Takeo Kanade

Details der Publikationsliste

Zeitraum

1956 - 9999

Anzahl

523

Co-Autoren

Incremental Acquisition of a Three-Dimensional Scene Model from Images, (9999)

Herman,Martin, Kanade,Takeo, Kuroe,Shigeru

We describe the current state of the 3D Mosaic project, whose goal is to incrementally acquire a 3D model of a complex urban scene from images. The notion of incremental acquisition arises from the...

Gradient Space Under Orthography and Perspective, (9999)

Shafer,Steven A., Kanade,Takeo, Kender,John R.

Mackworth's gradient space has proven to be a useful tool for image understanding. However, descriptions of its important properties have been somewhat scattered in the literature. This paper...

The Theory of Straight Homogeneous Generalized Cylinders, (9999)

Shafer,Steven A., Kanade,Takeo

In recent years, Binford's generalized cylinders have become an important tool for imagine understanding. However, research has been hampered by a lack of analytical results for these shapes. In this...

Adapting Optical-Flow to Measure Object Motion in Reflectance and X-Ray Image Sequences, (9999)

Cornelius,Nancy, Kanade,Takeo

This paper adapts a previous work on optical flow to the problem of determining arbitrary motions of objects from 2-dimensional image sequences. The method allows for gradual changes in the way an...

Motion Planning (2009)

Takeo Kanade, Richard Paul, Jean-claude Latombe

One important goal in robotics is to make it possible for robots to perfonn tasks whose goals are expressed in high-level declarative terms. In this context, researchers in motion planning develop...

Nonrigid Structure from Motion in Trajectory Space (2009)

Ijaz Akhter, Sohaib Khan, Yaser Sheikh, Takeo Kanade

Existing approaches to nonrigid structure from motion assume that the instantaneous 3D shape of a deforming object is a linear combination of basis shapes, which have to be estimated anew for each...

The thrust of the VSAM Integrated Feasibility (2009)

Takeo Kanade, Robert T. Collins, Alan J. Lipton

Carnegie Mellon University (CMU) and the Sarno Corporation (Sarno) are performing an integrated feasibility demonstration of Video Surveillance and Monitoring (VSAM). The objective istodevelop a...

Computational Intelligence io Robotics and Automation July 16-20,2003, Kobe, Japan Measurement and Comparison of Human and Humanoid Walking Abstract (2008)

Satoshi Kagami, Masaaki Mochimarul, Yoshihiro Ehara, Koichi Nishiwaki, Takeo Kanade, Hirochika Inoue

This paper describes our research efforts aimed at un-derstanding human being walking functions. Using mo-tion capture system, force plates and distributed force sensors, both human being and...

A correlation-based model prior for stereo (2008)

Yanghai Tsin, Takeo Kanade

All non-trivial stereo problems need model priors to deal with ambiguities and noise perturbations. To meet requirements of increasingly demanding tasks such as modeling for rendering, a proper model...

13 (2008)

Gerhard Goos, Juris Hartmanis, Jan Van Leeuwen, Editorial Board, David Hutchison, Takeo Kanade, ...

concerned, specifically the rights of translation, reprinting, re-use of illustrations, recitation, broadcasting, reproduction on microfilms or in any other way, and storage in data banks....

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,VOL. 22,NO. 7,JULY 2000 1 A Cooperative Algorithm for Stereo Matching and Occlusion Detection (2008)

C. Lawrence Zitnick, Takeo Kanade

AbstractÐThis paper presents a stereo algorithm for obtaining disparity maps with occlusion explicitly detected. To produce smooth and detailed disparity maps,two assumptions that were originally...

Projector Calibration using Arbitrary Planes and Calibrated Camera (2008)

Makoto Kimura, Masaaki Mochimaru, Takeo Kanade

In this paper, an easy calibration method for projector is proposed. The calibration handled in this paper is projective relation between 3D space and 2D pattern, and is not correction of trapezoid...

KANADE T.: Inverse Volume Rendering Approach to 3D Reconstruction from Multiple Images (2008)

Shuntaro Yamazaki, Masaaki Mochimaru, Takeo Kanade

Abstract. This paper presents a method of image-based 3D modeling for intricately-shaped objects, such as a fur, tree leaves and human hair. We formulate the imaging process of these small geometric...

PAPER Human Foot Reconstruction from Multiple Camera Images with Foot Shape Database (2008)

Jiahui Wang †a, Makoto Kimura, Masaaki Mochimaru, Takeo Kanade

SUMMARY Recently, researches and developments for measuring and modeling of the human body have been receiving much attention. Our aim is to reconstruct an accurate shape of a human foot from...

Statistical Shape Models for Object Recognition and Part Localization (2008)

Yan Li, Yanghai Tsin, Yakup Genc, Takeo Kanade

This paper deals with part-based object recognition. We present a statistical shape model that characterizes both variations intrinsic to an object class and perturbations unique to each observation....

Image Segmentation Using Iterated Graph Cuts BasedonMulti-scaleSmoothing (2008)

Tomoyuki Nagahashi, Hironobu Fujiyoshi, Takeo Kanade

Abstract. We present a novel approach to image segmentation using iterated Graph Cuts based on multi-scale smoothing. We compute the prior probability obtained by the likelihood from a color...

Abstract Human Operational Errors in a Virtual Driver Simulation (2008)

Toru Nakata, Altion Simo, Koji Kitamura, Takeo Kanade

We propose a virtual user that simulates human machine interaction including errors in body actions and mistakes in cognitive decision. Occurrence of human error has deep relationships with control...

Downloaded from (2008)

James M. Rehg, Daniel D. Morris, Takeo Kanade, James M. Rehg, Daniel D. Morris, Takeo Kanade

Three-dimensional (3D) kinematic models are widely-used in videobased figure tracking. We show that these models can suffer from singularities when motion is directed along the viewing axis of a...

Relevance Feedback for Sketch Retrieval Based on Linear Programming Classification (2008)

Gerhard Goos, Juris Hartmanis, Jan Van Leeuwen, Editorial Board, ...

Abstract. Relevance feedback plays as an important role in sketch retrieval as it does in existing content-based retrieval. This paper presents a method of relevance feedback for sketch retrieval by...

Content-free Image Retrieval by Combinations of Keywords and User Feedbacks (2008)

Shingo Uchihashi, Takeo Kanade

Abstract. The performance of a new content-free approach to image retrieval is demonstrated. Accumulated user feedback data that specify which images are (ir)relevant to each other and keywords...

Name-It: Naming and Detecting Faces in Video by the Integration of Image and Natural Language Processing (2008)

Yuichi Nakamura Y, Takeo Kanade

We have been developing Name-It, a system that associates faces and names in news videos. First, as the only knowledge source, the system is given news videos which include image sequences and...

Use of Automated Facial Image Analysis for Measurement of Emotion Expression (2008)

The H, Jeffrey F. Cohn, Takeo Kanade

expressions serve interpersonal functions of emotion by conveying communicative intent, signaling affective information in social referencing (Campos, Bertenthal, & Kermoian, 1992), and more...

Learning to Track Multiple People in Omnidirectional Video. ∗ (2008)

Fernando De, Torre Carlos, Vallespi Paul, E. Rybski, Manuela Veloso, Takeo Kanade

Abstract — Meetings are a very important part of everyday life for professionals working in universities, companies or governmental institutions. We have designed a physical awareness system called...

Precision Freehand Sculpting of Bone (2008)

Gabriel Brisson, Takeo Kanade, Anthony Digioia, Branislav Jaramaz

Abstract. The Precision Freehand Sculptor (PFS) is a compact, handheld, intelligent tool to assist the surgeon in accurately cutting bone. A retractable rotary blade on the PFS allows a computer to...

To Appear in the IEEE Transactions on Pattern Analysis and Machine Intelligence Limits on Super-Resolution and How to Break Them (2008)

Simon Baker, Takeo Kanade

Nearly all super-resolution algorithms are based on the fundamental constraints that the super-resolution image should generate the low resolution input images when appropriately warped and...

Parameterizing Homographies CMU-RI-TR-06-11 (2008)

Simon Baker, Ankur Datta, Takeo Kanade

The motion of a plane can be described by a homography. We study how to parameterize homographies to maximize plane estimation performance. We compare the usual 3 × 3 matrix parameterization with a...

AUTOMATIC CLUSTERING OF FACES IN MEETINGS (2008)

Carlos Vallespi, Manuela Veloso, Takeo Kanade

Meetings are an integral part of business life for any organization. In previous work, we have developed a physical awareness system called CAMEO (Camera Assisted Meeting Event Observer) to record...

Applications to Human Modeling and Markerless Motion Tracking (2008)

Simon Baker, Takeo Kanade, Simon Baker, Takeo Kanade

¡  ¢  Systems and Experiments Paper   £  ¡ In Part I of this paper we developed the theory and algorithms for performing Shape-From-Silhouette (SFS) across time. In this second part, we show...

KANADE T.: Inverse Volume Rendering Approach to 3D Reconstruction from Multiple Images (2008)

Shuntaro Yamazaki, Masaaki Mochimaru, Takeo Kanade

Abstract. This paper presents a method of image-based 3D modeling for intricately-shaped objects, such as a fur, tree leaves and human hair. We formulate the imaging process of these small geometric...

To Appear in the ACM Transactions on Graphics Image-Based Spatio-Temporal Modeling and View Interpolation of Dynamic Events (2008)

Sundar Vedula, Simon Baker, Takeo Kanade

We present an approach for modeling and rendering a dynamic, real-world event from an arbitrary viewpoint, and at any time, using images captured from multiple video cameras. The event is modeled as...

AFactorization Method for A ne Structure from Line Correspondences (2008)

Long Quan, Takeo Kanade

A family of structure from motion algorithms called the factorization method has been recently developed from the orthographic projection model to the a ne camera model [23, 16, 18]. All these...

Manuscript for T.Sato, T.Kanade, E.Hughes, and M.Smith, “Video OCR for Digital News Archives”, IEEE Workshop on Content-Based Access of Image and Video Databases (CAIVD’98), Bombay,India,pp.52-60,January,1998 Video OCR for Digital News Archives (2008)

Toshio Sato, Takeo Kanade, Ellen K. Hughes, Michael A. Smith

Video OCR is a technique that can greatly help to locate topics of interest in a large digital news video archive via the automatic extraction and reading of captions and annotations. News captions...

Appearance Based Prosthetic Eye (2008)

Naho Inamoto, Takeo Kanade, Hideo Saito

This paper introduces a new approach to improve the appearance of a prosthetic eye using computer vision and graphics technology. The proposed method can synthesize realistic appearance and movement...

Proceedings of 2005 5th IEEE-RAS International Conference on Humanoid Robots Vision-Guided Humanoid Footstep Planning for Dynamic Environments (2008)

Joel Chestnutt, James Kuffner, Takeo Kanade

Abstract — Despite the stable walking capabilities of modern biped humanoid robots, their ability to autonomously and safely navigate obstacle-filled, unpredictable environments has so far been...

In press in Behavior Research Methods, Instruments, and Computers. 1 Automatic Recognition of Eye Blinking in Spontaneously Occurring Behavior (2008)

Jeffrey F. Cohn, Jing Xiao, Tsuyoshi Moriyama, Zara Ambada, Takeo Kanade

Previous research in automatic facial expression recognition has been limited to recognition of gross expression categories (e.g., joy or anger) in posed facial behavior under well-controlled...

Recovery of Dynamic Scene Structure from Multiple Image Sequences (2008)

Peter W. R, P. J. Narayanan, Takeo Kanade

Despite significant progress in automatic recovery of static scene structure from range images, little effort has been made toward extending these approaches to dynamic scenes. This disparity is in...

Cell population tracking and lineage construction with spatiotemporal context (2008)

Kang Li, Mei Chen, Takeo Kanade

Abstract. Automated visual-tracking of cell populations in vitro using phase contrast time-lapse microscopy is vital for quantitative, systematic and high-throughput measurements of cell behaviors....

2 (2008)

Anthony M. Digioia, Branislav Jaramaz, David A. Simon, Fritz Morgan, James E. Moody, Bruce D. Colgan, ...

Dislocation following total hip replacement surgery (THR) remains a significant clinical problem. Malposition of the acetabular component increases the occurrence of impingement, reduces the “safe...

To appear in IEEE Transactions on Pattern Analysis and Machine Intelligence The Asymmetry of Image Registration and its Application to Face Tracking (2008)

Takeo Kanade, Simon Baker

Most image registration problems are formulated in an asymmetric fashion. Given a pair of images, one is implicitly or explicitly regarded as a template, and warped onto the other to match as well as...

AUTOMATIC CLUSTERING OF FACES IN MEETINGS (2008)

Carlos Vallespi, Manuela Veloso, Takeo Kanade

Meetings are an integral part of business life for any organization. In previous work, we have developed a physical awareness system called CAMEO (Camera Assisted Meeting Event Observer) to record...

Multimedia Systems Manuscript Nr. (will be inserted by hand later) Video OCR: Indexing Digital News Libraries by Recognition of Superimposed Caption (2008)

Toshio Sato, Takeo Kanade, Ellen K. Hughes, Michael A. Smith

Abstract. The automatic extraction and reading of news captions and annotations can be of great help locating topics of interest in digital news video archives. To achieve this goal, we present a...

Name-It: Naming and Detecting Faces in Video by the Integration of Image and Natural Language Processing (2008)

Yuichi Nakamura Y, Takeo Kanade

We have been developing Name-It, a system that associates faces and names in news videos. First, as the only knowledge source, the system is given news videos which include image sequences and...

In Proceedings, 2002 Medical Image Computing and Computer Assisted Intervention (MICCAI), Montreal, 2003. Weakly-Supervised Segmentation of Non-Gaussian Images via Histogram Adaptation (2008)

Jonas August, Takeo Kanade

Abstract. Here we apply an active contour model that allows for arbitrary intensity distributions inside and outside the boundary of an object to be segmented in an image. Computationally, we...

Chinese Academy of Sciences, (2008)

Ying-li Tian, Jeffrey F. Cohn, Takeo Kanade

Accurately tracking facial features requires coping with the large variation in appearance across subjects and the combination of rigid and non-rigid motion. In this paper, we describe our work...

Medical Image- Atlas Registration Using Deformable Models for Anomaly Detection (2008)

Mei Chen, Takeo Kanade, Dean Pomerleau

Abstract 1 We introduce a system that automatically segments and classifies structures in brain MRI volumes. It segments 144 structures of a 256x256x124 voxel image in 18 minutes on an SGI computer...

1.1 The Computational Burden of Regularized (2008)

Jonas August, Takeo Kanade

X-ray computerized tomography (CT) and related imaging modalities (e.g., PET) are notorious for their excessive computational demands, especially when noise-resistant probabilistic methods such as...

Submitted to the IEEE Transactions on Pattern Analysis and Machine Intelligence Three-Dimensional Scene Flow (2008)

Sundar Vedula, Simon Baker, Peter R, Robert Collins, Takeo Kanade, Simon Baker

Just as optical flow is the two-dimensional motion of points in an image, scene flow is the three-dimensional motion of points in the world. The fundamental difficulty with optical flow is that only...

Computational model of dic microscopy: From observations to measurements (2008)

Farhana Kagalwala, Frederick Lanni, Takeo Kanade

Although Di erential Interference Contrast (DIC) microscopy isapowerful visual-ization tool used to study live biological cells, its use so far has been limited to qual-itative observations. The...

Medical Image- Atlas Registration Using Deformable Models for Anomaly Detection (2008)

Mei Chen, Takeo Kanade, Dean Pomerleau

Abstract 1 We introduce a system that automatically segments and classifies structures in brain MRI volumes. It segments 144 structures of a 256x256x124 voxel image in 18 minutes on an SGI computer...

Chapter 11. Facial Expression Analysis (2008)

Ying-li Tian, Takeo Kanade, Jeffrey F. Cohn

Facial expressions are the facial changes in response to a person’s internal emotional states, intentions, or social communications. Facial expression analysis has been an active research topic for...

Historical Perspectives on 4D Virtualized Reality (2008)

Takeo Kanade, P. J. Narayanan

Recording dynamic events, such as a sports event, a ballet performance, or a lecture, digitally for experiencing in a spatiotemporally distant setting requires 4D capture: three dimensions for their...

The thrust of the VSAM Integrated Feasibility (2008)

Takeo Kanade, Robert T. Collins, Alan J. Lipton

Carnegie Mellon University (CMU) and the Sarno Corporation (Sarno) are performing an integrated feasibility demonstration of Video Surveillance and Monitoring (VSAM). The objective istodevelop a...

\Lambda (2008)

Yasuyoshi Yokokohji, Ralph L. Hollis, Takeo Kanade

Haptic interfaces have been recognized as im- portant input/output channels to/from the virtual environment[10][11][16]. Usually a haptic interface is implemented with a visual display interface such...

\Lambda Radiologic Sciences (2008)

Yanxi Liu, Takeo Kanade

ABSTRACT A content-based 3D neuroradiologic image retrievalsystem is being developed at the Robotics Institute of CMU. The special characteristics of this system in-clude: 1) directly dealing with...

Chapter 1 SUPER-RESOLUTION: LIMITS AND BEYOND (2008)

Simon Baker, Takeo Kanade

A variety of super-resolution algorithms have been described in this book. Most of them are based on the same source of information however; that the super-resolution image should generate the lower...

Learning to Track Multiple People in Omnidirectional Video. ∗ (2008)

Fernando De, Torre Carlos, Vallespi Paul, E. Rybski, Manuela Veloso, Takeo Kanade

Abstract — Meetings are a very important part of everyday life for professionals working in universities, companies or governmental institutions. We have designed a physical awareness system called...

Multimedia Systems Manuscript Nr. (will be inserted by hand later) Video OCR: Indexing Digital News Libraries by Recognition of Superimposed Captions (2008)

Toshio Sato, Takeo Kanade, Ellen K. Hughes, Michael A. Smith

Abstract. The automatic extraction and recognition of news captions and annotations can be of great help locating topics of interest in digital news video libraries. Toachieve this goal, we present a...

Modeling, Combining, and Rendering (2008)

Sundar Vedula, Peter R, Hideo Saito, Takeo Kanade

Virtualized Reality creates a model of time-varying real-world events from image sequences. The model can be used for manipulating and combining these events, and for rendering new virtual images. In...

Learning to Track Multiple People in Omnidirectional (2008)

Video Fernando De, Fernando De, Torre Carlos, Vallespi Paul, E. Rybski, Manuela Veloso, ...

Meetings are a very important part of everyday life for professionals working in universities, companies or governmental institutions. We have designed a physical awareness system called CAMEO...

Martial Hébert (2007)

Todd Andrew Williamson, Charles E. Thorpe, Takeo Kanade, Robert Bolles Sri

I have developed a method for obstacle detection in a highway environment using the CMU Video Rate Multi-Baseline Stereo Machine. One key feature of this method is the computation and output of a...

, and (2007)

Shigeyuki Baba, Sundar Vedula, Kong Man Cheung, Takeo Kanade

Abstract. We present appearance-based virtual view generation which allows viewers to y through a real dynamic scene. The scene is captured by synchronized multiple cameras. Arbitrary views are...

y (2007)

Daniel D. Morris, Kenichi Kanatani, Takeo Kanade

In computer vision we often estimate a 3D model of an object, and its uncertainty, up to an unknown scale factor. This unknown scale factor means that we cannot directly infer positions and lengths...

Computational model of dic microscopy: From observations to measurements (2007)

Farhana Kagalwala, Frederick Lanni, Takeo Kanade

Although Differential Interference Contrast (DIC) microscopy is a powerful visualization tool used to study live biological cells, its use so far has been limited to qualitative observations. The...

The Factorization Method with Linear Motions (2007)

Mei Han, Takeo Kanade

In this paper we describe the factorization method with linear motions. We design an unified representation of scene structure and moving objects by assuming that the objects are moving linearly and...

CMU-CS-95-158R (2007)

Henry A. Rowley, Shumeet Baluja, Takeo Kanade

We present a neural network-based face detection system. A retinally connected neural network examines small windows of an image, and decides whether each window contains a face. The system...

1 (2007)

Robert T. Collins, Alan J. Lipton, Takeo Kanade, Hironobu Fujiyoshi, David Duggins, Yanghai Tsin, ...

Under the three-year Video Surveillance and Monitoring (VSAM) project (1997--1999), the

An Image Overlay System for Medical Data (2007)

Mike Blackwell, Constantinos Nikou, Anthony M. Digioia, Takeo Kanade

Image Overlay is a computer display technique which superimposes computer images over the viewer’s direct view of the real world. The positions of the viewer’s head, objects in the environment,...

analysis, obstacle avoidance (2007)

Adrian Broadhurst, Simon Baker, Takeo Kanade

A prediction and planning framework for road safety

Calibration Method for Determining the Physical Location of the Ultrasound Image Plane (2007)

Devin V. Amin, Takeo Kanade, Branislav Jaramaz, Ph. D, Ph. D, Ph. D

Abstract. This paper describes a calibration method for determining the physical location of the ultrasound (US) image plane relative to a rigidly attached 3D position sensor. A calibrated US probe...

Textureless Layers CMU-RI-TR-04-17 (2007)

Qifa Ke, Simon Baker, Takeo Kanade

Layers are one of the most well studied ways of representing a 3D scene. Although man-made scenes often contain constant intensity planar regions (textureless layers), it is almost always assumed...

ARTIFICIAL INTELLIGENCE A Theory of Origami World* (2007)

Takeo Kanade, Recommended Harry Barrow

The recovery of three-diniensional configurations ofa scene from its image is one of the most important stcps in coniputer vision. The Origami world is a model for understanding line drawings in...

Martial Hebert and Takeo Kanade (2007)

Charles Thorpe, Chades Thorpe, Jill Crisman, Takahiro Fujimori, Takeo Kanade, Takeo Kanade, ...

5351, and monitored by the U.S. Army Engineer Topographc Laboratories under contract DACA76-85-

3 * (2007)

Pradeep K. Khosla, Takeo Kanade

The manipulator trajectory tracking control problem revolves around computing the torques to be applied to achieve accu-rate tracking. This problem has been extensively studied in simulations, but...

Robotics Institute. (2007)

Assoc Mem Asme, Takeo Kanade, Schenley Park

Present electrically powered manipulators are still far inferior to human arms and unsatisfactory for many ap-plications in terms of speed, accuracy and versatility. One of the reasons for this poor...

0 c submitted to International Journal of-Robotics and Automation. Also presented- at CDC, 1985. An Algorithm to Estimate Manipulator Dynamics Parameters' (2007)

Pradeep K. Khosla, Takeo Kanade

This paper presents algorithms for identifying parameters of an N degrees-of-freedom robotic manipulator. First, we outline the fundamental properties of the Newton-Euler formulation of robot...

Carnegie Mellon 'University (2007)

Mei Han, Takeo Kanade

' We describe a reconstruction method of multiple motion scenes, which are the scenes containing multiple ' moving objects, from uncalibrated views. Assuming that the objects' are...

International (2007)

Omead Amidi, Takeo Kanade, Ryan Miller

This paper presents an overview of the Autonomous Helicopter Project at Carnegie Mellon Robot-ics Institute. The advantages of an autonomous vision-guided helicopter for a number of goal applications...

Elsevier ARTINT 1002 From a real chair to a negative (2007)

Takeo Kanade, How It Started, T. Kanade

In the fall of 1977, I was invited by Raj Reddy to spend a year at the

14 Cpmputer Vision Physical Science (2007)

Takeo Kanade

as a Vision is one of the most important perceptual capabilities that any autonomous

Representation and Control in Vision (2007)

Takeo Kanade

One of the central issues in vision is how to reprcscnt and use knowlcdgc relevant to understanding the imagc. Partly bccausc vision is so difficult. and partly bccausc ecn the chcapcst solutions can...

Sensory Computing (2007)

Vladimir Brajovic, Takeo Kanade

Computation in artificial perceptual systems assumes that appropriate and reliable sensory information about the environment is available. However, today’s sensors cannot guarantee optimal...

Integrated Vision and Sensing for Human Sensory Augmentation (2007)

Takeo Kanade, Vladimir Brajovic

sponsored by ONR performs multi-disciplinary research in integrating vision algorithms with sens-ing technology for low-power, low-latency, com-pact adaptive vision systems. These are crucial...

I ARTIFICIAL INTELLIGENCE 289 Incremental Reconstruction of 3D Scenes from Multiple, Complex Images* (2007)

Martin Herman, Takeo Kanade

The 3 D Mosaic system is a vision system &at incremenmlly reconstructs complex 3 D scenes from a sequence of images obtained from mdtiple vKwpoints. The system encompasses several levels of the...

An Optical Proximity Sensor for Measuring Surface Position and Orientation for Robot Manipulation (2007)

Takeo Kanade, Thomas M. Sommer

of Naval Research. We have developed a noncontact proximity sensor which can measure the distance and orientatiorr of a surface in a range of four to jive centimeters. The sensor is based on the...

Abstract (2007)

Ellen Lowenfeld, Walker Martin Herman, Takeo Kanade

The capabilities for representing and reasoning about three-dimensional objects are essential for. knowledge-based, 30 photo-interpretation systems that combine domain knowledge with image...

ARTIFICIAL INTELLIGENCE 289 Incremental Reconstruction of 3D Scenes from Multiple, Complex Images* (2007)

Martin Herman, Takeo Kanade

The 3D Mosaic system is a vision system that incrementally reconstructs complex 30scenes from a sequence of images obtained from multiple viewpoints. The system encompasses several levels of the...

Submitted to the IEEE Transactions on Pattern Analysis and Machine Intelligence Limits on Super-Resolution and How to Break Them (2007)

Simon Baker, Takeo Kanade

Nearly all super-resolution algorithms are based on the fundamental constraints that the super-resolution image should generate the low resolution input images when appropriately warped and...

Computer Vision, 2002. Object Detection Using the Statistics of Parts (2007)

Henry Schneiderman, Takeo Kanade

In this paper we describe a trainable object detector and its instantiations for detecting faces and cars at any size, location, and pose. To cope with variation in object orientation, the detector...

To Appear in the IEEE Transactions on Pattern Analysis and Machine Intelligence Limits on Super-Resolution and How to Break Them (2007)

Simon Baker, Takeo Kanade

Nearly all super-resolution algorithms are based on the fundamental constraints that the super-resolution image should generate the low resolution input images when appropriately warped and...

Abstract Modeling, Combining, and Rendering Dynamic Real-World Events From Image Sequences (2007)

Sundar Vedula, Peter R, Hideo Saito, Takeo Kanade

Virtualized Reality creates a model of time-varying real-world events from image sequences. The model can be used for manipulating and combining these events, and for rendering new virtual images. In...

From the Proceedings of the 2001 IEEE-EURASIP Workshop On Nonlinear Signal and Image Processing SUPER-RESOLUTION: RECONSTRUCTION OR RECOGNITION? (2007)

Simon Baker, Takeo Kanade

Super-resolution is usually posed as a reconstruction problem. The low resolution input images are assumed to be noisy, downsampled versions of an unknown super-resolution image that is to be...

FACS Coding Algorithms A Comparative Study of Alternative FACS Coding Algorithms (2007)

Jeffrey F. Cohn, Takeo Kanade, Tsuyoshi Moriyama, Zara Ambadar, Jing Xiao, Jiang Gao, ...

Two groups were contracted to experiment with coding of FACS (Ekman & Friesen, 1978) action units on a common database. One group is ours at CMU and the University of Pittsburgh, and the other is...

Abstract Statistical Calibration of CCD Imaging Process (2007)

Yanghai Tsin, Visvanathan Ramesh, Takeo Kanade

Charge-Coupled Device (CCD) cameras are widely used imaging sensors in computer vision systems. Many photometric algorithms, such as shape from shading, color constancy, and photometric stereo,...

Abstract Modeling, Combining, and Rendering Dynamic Real-World Events From Image Sequences (2007)

Sundar Vedula, Peter R, Hideo Saito, Takeo Kanade

Virtualized Reality creates time-varying three-dimensional models and virtual images from image sequences. In this paper, we present two recent enhancements to Virtualized Reality. We present Model...

EigenFairing: 3D Model Fairing using Image Coherence (2007)

Pragyana Mishra, Omead Amidi, Takeo Kanade

A surface is often modeled as a triangulated mesh of 3D points and textures associated with faces of the mesh. The 3D points could be either sampled from range data or derived from a set of images...

Spatio-Temporal Frequency Analysis for Removing Rain and Snow from Videos (2007)

Barnum, Peter, Kanade, Takeo, Narasimhan, Srinivasa

Capturing good videos outdoors can be challenging due to harsh lighting, unpredictable scene changes, and most relevant to this work, dynamic weather. Particulate weather, such as rain and snow,...

Spatio-Temporal Frequency Analysis for Removing Rain and Snow from Videos (2007)

Barnum, Peter, Kanade, Takeo, Narasimhan, Srinivasa

Capturing good videos outdoors can be challenging due to harsh lighting, unpredictable scene changes, and most relevant to this work, dynamic weather. Particulate weather, such as rain and snow,...

GPU-accelerated real-time 3D tracking for humanoid locomotion (2007)

Joel Chestnutt, Satoshi Kagami, Koichi Nishiwaki, James Kuffner, Takeo Kanade

Abstract — For humanoid robots to fully realize their biped potential in a three-dimensional world and step over, around or onto obstacles such as stairs, appropriate and efficient approaches to...

Seeing the World Behind the Image: Spatial Layout for 3D Scene Understanding (2007)

Derek Hoiem, Alexei A. Efros, Takeo Kanade

When humans look at an image, they see not just a pattern of color and texture, but the world behind the image. In the same way, computer vision algorithms must go beyond the pixels and reason about...

Sensor Placement Design for Object Pose Determination with Three Light- Stripe Range Finders (2006)

Kemmotsu, Keiichi, Kanade, Takeo

The pose of a polyhedral object can be determined with range data obtained from a set of simple light-stripe range sensors. However, localization results are highly dependent on sensor placement....

A Sequential Factorization Method for Recovering Shape and Motion from Image Streams (2006)

Morita, Toshihiko, Kanade, Takeo

We present a sequential factorization method for recovering the three-dimensional shape of an object and the motion of the camera from a sequence of images, using tracked features. The factorization...

A Paraperspective Factorization Method for Shape and Motion Recovery (2006)

Poelman, Conrad J., Kanade, Takeo

The factorization method, first developed by Tomasi and Kanade, recovers both the shape of an object and its motion from a sequence of images, using many images and tracking many feature points to...

An Active Multibaseline Stereo System with Real-Time Image Acquisition (2006)

Kang, Sing B., Webb, Jon, Zitnick, C. L., Kanade, Takeo

We describe our four-camera multibaseline stereo system in a convergent configuration and our implementation of a parallel depth recovery scheme for this system. Our system is capable of image...

Online environment reconstruction for biped navigation (2006)

Joel Chestnutt, Satoshi Kagami, Koichi Nishiwaki, James Kuffner, Takeo Kanade

Abstract — As navigation autonomy becomes an increasingly important research topic for biped humanoid robots, efficient approaches to perception and mapping that are suited to the unique...

The Asymmetry of Image Registration and its Application to Face Tracking. Robotics Institute (2006)

Takeo Kanade, Simon Baker

Most image registration problems are formulated in an asymmetric fashion. Given a pair of images, one is implicitly or explicitly regarded as a template, and warped onto the other to match as well as...

Online Environment Reconstruction (2006)

For Biped Navigation, Joel Chestnutt, Satoshi Kagami, Koichi Nishiwaki, James Kuffner, Takeo Kanade

As navigation autonomy becomes an increasingly important research topic for biped humanoid robots, efficient approaches to perception and mapping that are suited to the unique characteristics of...

Discriminative cluster analysis (2006)

Takeo Kanade

Clustering is one of the most widely used statistical tools for data analysis. Among all existing clustering techniques, k-means is a very popular method because of its ease of programming and...

T.: Online tracking of migrating and proliferating cells imaged with phase-contrast microscopy (2006)

Kang Li, Eric D. Miller, Lee E. Weiss, Phil G. Campbell, Takeo Kanade

Automated visual-tracking of cell population in vitro using phase-contrast time-lapse microscopy is vital for the quantitative and systematic study of cell behaviors, including spatiotemporal...

Virtual touch: An efficient registration method for catheter navigation in left atrium (2006)

Hua Zhong, Takeo Kanade, David Schwartzman

Abstract. In this paper, we present a left atrium registration system which utilizes a 3D intra-cardiac ultrasound catheter for faster (more than 700 times) and higher quality surface registration...

Resolution-Aware Fitting of Active Appearance Models to Low Resolution Images (2006)

Simon Baker, Takeo Kanade

Abstract. Active Appearance Models (AAM) are compact representations of the shape and appearance of objects. Fitting AAMs to images is a difficult, non-linear optimization task. Traditional...

Meticulously detailed eye region model and its application to analysis of facial images (2006)

Tsuyoshi Moriyama, Takeo Kanade, Jing Xiao, Jeffrey F. Cohn

Abstract—We propose a system that is capable of detailed analysis of eye region images in terms of the position of the iris, degree of eyelid opening, and the shape, complexity, and texture of the...

Uncertainty models in quasiconvex optimization for geometric reconstruction (2006)

Qifa Ke, Takeo Kanade

Geometric reconstruction problems in computer vision can be solved by minimizing the maximum of reprojection errors, i.e., the L∞-norm. Unlike L2-norm (sum of squared reprojection errors), the...

Discriminative cluster analysis (2006)

Takeo Kanade

Clustering is one of the most widely used statistical tools for data analysis. Among all existing clustering techniques, k-means is a very popular method because of its ease of programming and...

The Asymmetry of Image Registration and its Application to Face Tracking. Robotics Institute (2006)

Takeo Kanade, Simon Baker

Most image registration problems are formulated in an asymmetric fashion. Given a pair of images, one is implicitly or explicitly regarded as a template, and warped onto the other to match as well as...

Human Foot Reconstruction from Multiple Camera Images with Foot Shape Database (2006)

WANG, Jiahui, SAITO, Hideo, KIMURA, Makoto, MOCHIMARU, Masaaki, KANADE, Takeo

Recently, researches and developments for measuring and modeling of the human body have been receiving much attention. Our aim is to reconstruct an accurate shape of a human foot from multiple camera...

Shape-from-silhouette across time part I: Theory and algorithms (2005)

Simon Baker, Takeo Kanade

Shape-From-Silhouette (SFS) is a shape reconstruction method which constructs a 3D shape estimate of an object using silhouette images of the object. The output of a SFS algorithm is known as the...

Multi-view aam fitting and camera calibration (2005)

Seth Koterba, Simon Baker, Iain Matthews, Changbo Hu, Jing Xiao, Jeffrey Cohn, ...

In this paper we study the relationship between multiview Active Appearance Model (AAM) fitting and camera calibration. In the first part of the paper we propose an algorithm to calibrate the...

On-line Robot Adaptation to Environmental Change (2005)

Scott Lenser, Manuela Veloso (chair, Takeo Kanade, Sebastian Thrun

Robots performing tasks constantly encounter changing environmental conditions. These changes in the environment vary from the dramatic, such as rearrangement of furniture, to the subtle, such as a...

Content-free image retrieval based on relations exploited from user feedbacks (2005)

Shingo Uchihashi, Takeo Kanade

We propose a new “content-free ” image retrieval method which attempts to exploit certain common tendencies that exist among people’s interpretation of images from user feedbacks. The system...

On-line Robot Adaptation to Environmental Change (2005)

Scott Lenser, Takeo Kanade, Anthony Stentz

Robots performing tasks constantly encounter changing environmental conditions. These changes in the environment vary from the dramatic, such as rearrangement of furniture, to the subtle, such as a...

Quasiconvex optimization for robust geometric reconstruction (2005)

Qifa Ke, Takeo Kanade

Geometric reconstruction problems in computer vision are often solved by minimizing a cost function that combines the reprojection errors in the 2D images. In this paper, we show that, for various...

T.: Robust L1 norm factorization in the presence of outliers and missing data by alternative convex programming (2005)

Qifa Ke, Takeo Kanade

Matrix factorization has many applications in computer vision. Singular Value Decomposition (SVD) is the standard algorithm for factorization. When there are outliers and missing data, which often...

D.: Sensor guided ablation procedure for left atrium endocardium (2005)

Hua Zhong, Takeo Kanade, David Schwartzman

Abstract. In this paper, we present a sensor guided ablation procedure of highly motile left atrium. It uses a system which automatically registers the 4D heart model with the position sensor on the...

Quasiconvex optimization for robust geometric reconstruction (2005)

Qifa Ke, Takeo Kanade

Abstract—Geometric reconstruction problems in computer vision are often solved by minimizing a cost function that combines the reprojection errors in the 2D images. In this paper, we show that, for...

Omnidirectional Video Capturing, Multiple People Tracking and Identification for Meeting Monitoring. (2005)

Fernando De, Torre Carlos, Vallespi Paul, E. Rybski, Manuela Veloso, Takeo Kanade

Meetings are a very important part of every days life for professionals working in universities, companies or governmental institutions. In fact, it is estimated that a midlevel manager or...

Quasiconvex optimization for robust geometric reconstruction (2005)

Qifa Ke, Takeo Kanade

The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the Carnegie Mellon...

The role of non-overlap in image registration (2005)

Jonas August, Takeo Kanade

Abstract. Here we model the effect of non-overlapping voxels on image registration, and show that a major defect of overlap-only models—their limited capture range—can be alleviated....

On the Source of Asymmetry in Image Registration Problems. Robotics Institute (2005)

Takeo Kanade

Abstract. Most image registration problems are formulated in an asymmetric fashion. Given a pair of images, one is implicitly or explicitly regarded as template, and warped onto the other to match....

Quasiconvex optimization for robust geometric reconstruction (2005)

Qifa Ke, Takeo Kanade

Geometric reconstruction problems in computer vision are often solved by minimizing a cost function that combines the reprojection errors in the 2D images. In this paper, we show that, for various...

Footstep planning for the Honda ASIMO humanoid (2005)

Joel Chestnutt, Manfred Lau, German Cheung, James Kuffner, Jessica Hodgins, Takeo Kanade

Abstract — Despite the recent achievements in stable dynamic walking for many humanoid robots, relatively little navigation autonomy has been achieved. In particular, the ability to autonomously...

Vision-guided humanoid footstep planning for dynamic environments (2005)

Joel Chestnutt, James Kuffner, Takeo Kanade

Abstract — Despite the stable walking capabilities of modern biped humanoid robots, their ability to autonomously and safely navigate obstacle-filled, unpredictable environments has so far been...

On the Source of Asymmetry in Image Registration Problems. Robotics Institute (2005)

Takeo Kanade

Abstract. Most image registration problems are formulated in an asymmetric fashion. Given a pair of images, one is implicitly or explicitly regarded as template, and warped onto the other to match....

Multi-view aam fitting and camera calibration (2005)

Seth Koterba, Simon Baker, Iain Matthews, Changbo Hu, Jing Xiao, Jeffrey Cohn, ...

In this paper we study the relationship between multiview Active Appearance Model (AAM) fitting and camera calibration. In the first part of the paper we propose an algorithm to calibrate the...

A closed-form solution to non-rigid shape and motion recovery (2004)

Jing Xiao, Jin-xiang Chai, Takeo Kanade

Abstract. Recovery of three dimensional (3D) shape and motion of non-static scenes from a monocular video sequence is important for applications like robot navigation and human computer interaction....

Fitting a single active appearance model simultaneously to multiple images (2004)

Changbo Hu, Jing Xiao, Iain Matthews, Simon Baker, Jeffrey F. Cohn, Takeo Kanade

Active Appearance Models (AAMs) are a well studied 2D deformable model. One recently proposed extension of AAMs to multiple images is the Coupled-View AAM. Coupled-View AAMs model the 2D shape and...

Face recognition across pose and illumination (2004)

Ralph Gross, Simon Baker, Iain Matthews, Takeo Kanade

The last decade has seen automatic face recognition evolve from small scale research systems to a wide range of commercial products. Driven by the FERET face database and evaluation protocol, the...

Real-Time Non-Rigid Driver Head Tracking for Driver Mental State Estimation (2004)

Simon Baker, Iain Matthews, Jing Xiao, Ralph Gross, Takeo Kanade, Takahiro Ishikawa

The non-rigid motion of a driver's head (i.e. the motion of their mouth, eye-brows, cheeks, etc) can tell us a lot about their mental state; e.g. whether they are drowsy, alert, aggressive,...

Real-Time Non-Rigid Driver Head Tracking for Driver Mental State Estimation (2004)

Simon Baker, Iain Matthews, Jing Xiao, Ralph Gross, Takahiro Ishikawa, Takeo Kanade

The non-rigid motion of a driver's head (i.e. the motion of their mouth, eye-brows, cheeks, etc) can tell us a lot about their mental state; e.g. whether they are drowsy, alert, aggressive,...

Real-Time Combined 2D+3D Active Appearance Models (2004)

Jing Xiao, Simon Baker, Iain Matthews, Takeo Kanade

Active Appearance Models (AAMs) are generative models commonly used to model faces. Another closely related type of face models are 3D Morphable Models (3DMMs). Although AAMs are 2D, they can still...

High-Zoom Video Hallucination by Exploiting Spatio-Temporal Regularities (2004)

Goksel Dedeoglu, Takeo Kanade, Jonas August

In this paper, we consider the problem of super-resolving a human face video by a very high (16) zoom factor. Inspired by recent literature on hallucination and examplebased learning, we formulate...

Robust Subspace Clustering by Combined Use of kNND Metric and SVD Algorithm (2004)

Qifa Ke, Takeo Kanade

vision, such as image/video segmentation and pattern classification. The major issue in subspace clustering is to obtain the most appropriate subspace from the given noisy data. Typical methods...

People Detection and Tracking in High Resolution Panoramic Video Mosaic (2004)

Raju Patil, Paul E. Rybski, Takeo Kanade, Manuela M. Veloso

We have designed a physical awareness system called CAMEO, the Camera Assisted Meeting Event Observer, which consists of a multi-camera omnidirectional vision system designed to be used in meeting...

ON SAMPLING OF IMAGE-BASED RENDERING DATA (2004)

Cha Zhang, Takeo Kanade

Image-based rendering (IBR) generates novel views from images instead of 3D models. It can be considered as a process of sampling the light rays in the space and interpolating the ones in novel...

Passive driver gaze tracking with active appearance models (2004)

Takahiro Ishikawa, Simon Baker, Iain Matthews, Takeo Kanade

Monocular gaze estimation is usually performed by locating the pupils, and the inner and outer eye corners in the image of the driver’s head. Of these feature points, the eye corners are just as...

Passive driver gaze tracking with active appearance models (2004)

Takahiro Ishikawa, Simon Baker, Iain Matthews, Takeo Kanade

Passive gaze estimation is usually performed by locating the pupils, and the inner and outer eye corners in the image of the driver’s head. Of these feature points, the eye corners are just as...

User-Powered “Content-Free” Approach to Image Retrieval (2004)

Takeo Kanade, Shingo Uchihashi

Consider a stereotypical image-retrieval problem; a user submits a set of query images to a system and through repeated interactions during which the system presents its current choices and the user...

A closed-form solution to non-rigid shape and motion recovery (2004)

Jing Xiao, Jin-xiang Chai, Takeo Kanade

Abstract. Recovery ofthree dimensional (3D) shape and motion ofnon-static scenes from a monocular video sequence is important for applications like robot navigation and human computer interaction....

A closed-form solution to non-rigid shape and motion recovery (2004)

Jing Xiao, Jin-xiang Chai, Takeo Kanade

Abstract. Recovery of three dimensional (3D) shape and motion of non-static scenes from a monocular video sequence is important for applications like robot navigation and human computer interaction....

A correlation-based approach to robust point set registration (2004)

Yanghai Tsin, Takeo Kanade

Abstract. Correlation is a very effective way to align intensity images. We extend the correlation technique to point set registration using a method we call kernel correlation. Kernel correlation is...

A closed-form solution to non-rigid shape and motion recovery (2004)

Jing Xiao, Jin-xiang Chai, Takeo Kanade

Abstract. Recovery ofthree dimensional (3D) shape and motion ofnon-static scenes from a monocular video sequence is important for applications like robot navigation and human computer interaction....

Extracting Shape Reflectance of Lambertian, Specular, and Hybrid Surfaces (2003)

Nayar, Shree K., Ikeuchi, Katsushi, Kanade, Takeo

All existing shape extraction techniques that are based on photometric measurements rely on assumed surface reflection properties. A method is proposed for determining the shape of surfaces whose...

A master-slave system to acquire biometric imagery of humans at distance (2003)

Xuhui Zhou, Robert T. Collins, Takeo Kanade, Peter Metes

The Distant Human Identification (DHID) system is a masterslave, real-time surveillance system designed to acquire biometric imagery of humans at distance. A stationary wide field of view master...

When is the shape of a scene unique given its light-field: A fundamental theorem of 3D vision (2003)

Simon Baker, Terence Sim, Takeo Kanade

The complete set of measurements that could ever be used by a passive 3D vision algorithm is the plenoptic function or light-field. We give a concise characterization of when the light-field of a...

Robust subspace computation using l1 norm (2003)

Qifa Ke, Takeo Kanade

Linear subspace has many important applications in computer vision, such as structure from motion, motion estimation, layer extraction, object recognition, and object tracking. Singular Value...

A Closed-Form Solution to Non-Rigid Shape and Motion Recovery (2003)

Jing Xiao, Jin-xiang Chai, Takeo Kanade

Recovery of 3D sp e and motion ofnon-s7p4 son-s from a monocular videosdeop) is im ortant for a lications like human com uter interaction. If every oint in thes cene randomly deforms at each frame,...

Multi-subregion based probabilistic approach toward pose-invariant face recognition (2003)

Takeo Kanade, Akihiko Yamada

Current automatic facial recognition systems are not robust against changes in illumination, pose, facial expression and occlusion. In this paper, we propose an algorithm based on a probabilistic...

Robust subspace computation using l1 norm (2003)

Qifa Ke, Takeo Kanade

Linear subspace has many important applications in computer vision, such as structure from motion, motion estimation, layer extraction, object recognition, and object tracking. Singular Value...

A master-slave system to acquire biometric imagery of humans at distance (2003)

Xuhui Zhou, Robert T. Collins, Takeo Kanade, Peter Metes

The Distant Human Identification (DHID) system is a masterslave, real-time surveillance system designed to acquire biometric imagery of humans at distance. A stationary wide field of view master...

Robust Full-Motion Recovery of Head by Dynamic Templates and Re-registration Techniques (2003)

Jing Xiao, Tsuyoshi Moriyama, Takeo Kanade, Jeffrey F. Cohn

This paper presents a method to recover the full-motion (3 rotations and 3 translations) of the head from an input video using a cylindrical head model. Given an initial reference template of the...

Appearancebased virtual view generation from multicamera videos captured in the 3-D room (2003)

Hideo Saito, Shigeyuki Baba, Takeo Kanade

Abstract—We present an appearance-based virtual view generation method that allows viewers to fly through a real dynamic scene. The scene is captured by multiple synchronized cameras. Arbitrary...

Gradient Space under Orthography and Perspective, (2002)

Shafer,Steven A., Kanade,Takeo, Kender,John

Machworth's gradient space has proven to be a useful tool for image understanding. However, descriptions of its important properties have been somewhat scattered in the literature. This paper...

Incremental Acquisition of a Three-dimensional Scene Model from Images, (2002)

Herman,Martin, Kanade,Takeo, Kuroe,Shigeru

We describe the current state of the 3D Mosaic project, whose goal is to incrementally acquire a 3D model of a complex urban scene from images. The notion of incremental acquisition arises from the...

Design of Direct-Drive Mechanical Arms. (2002)

Asada,Haruhiko, Kanade,Takeo

This paper describes the design concept of a new robot based on the direct-drive method using rare-earth DC torque motors. Because these motors have high torque, light weight and compact size, we can...

Information Processing Research. (2002)

Ball,Eugene, Bentley,Jon, Habermann,Nico, Hibbard,Peter, Kanade,Takeo

This report documents DARPA-supported basic research in Carnegie-Mellon University's Computer Science Department during the period 1 January 1981 through December 1983, extended to 31 December 1984....

Experimental Evaluation of Nonlinear Feedback and Feedforward Control Schemes for Manipulators. (2002)

Khosla,Pradeep K., Kanade,Takeo

The manipulator trajectory tracking control problem revolves around computing the torques to be applied to achieve accurate tracking. While this problem has been extensively studied in simulations,...

Limits on super-resolution and how to break them (2002)

Simon Baker, Takeo Kanade

AbstractÐNearly all super-resolution algorithms are based on the fundamental constraints that the super-resolution image should generate the low resolution input images when appropriately warped and...

An active camera system for acquiring multi-view video (2002)

Robert T. Collins, Omead Amidi, Takeo Kanade

A system is described for acquiring multi-view video of a person moving through the environment. A real-time tracking algorithm adjusts the pan, tilt, zoom and focus parameters of multiple active...

Evaluation of Gabor-wavelet-based facial action unit recognition in image sequences of increasing complexity (2002)

Ying-li Tian, Takeo Kanade, Jeffrey F. Cohn

Previous work suggests that Gabor-wavelet-based methods can achieve high sensitivity and specificity for emotionspecified expressions (e.g., happy, sad) and single action units (AUs) of the Facial...

Automatic recognition of eye blinking in spontaneously occurring behavior (2002)

Tsuyoshi Moriyama, Takeo Kanade, Jeffrey F. Cohn, Jing Xiao, Zara Ambadar, Jiang Gao, ...

Previous research in automatic facial expression recognition has been limited to recognition of gross expression categories (e.g., joy or anger) in posed facial behavior under well-controlled...

Limits on super-resolution and how to break them (2002)

Simon Baker, Takeo Kanade

We analyze the super-resolution reconstruction constraints. In particular, we derive a sequence of results which all show that the constraints provide far less useful information as the magnification...

On-line Robot Adaptation to Environmental Change (2002)

Scott Lenser, Manuela Veloso (chair, Takeo Kanade, Sebastian Thrun

Robots performing tasks constantly encounter changing environmental conditions. These changes in the environment vary from the dramatic, such as rearrangement of furniture, to the subtle, such as a...

Spatio-temporal view interpolation (2002)

Sundar Vedula, Simon Baker, Takeo Kanade

We propose an algorithm for creating novel views of a non-rigidly varying dynamic event by combining images captured from different positions, at different times. The algorithm operates by combining...

Automatic Recognition of Eye Blinking in Spontaneously Occurring Behavior (2002)

Tsuyoshi Moriyama Takeo, Takeo Kanade, Jeffrey F. Cohn, Jing Xiao, Zara Ambadar, Jiang Gao, ...

Previous research in automatic facial expression recognition has been limited to recognition of gross expression categories (e.g., joy or anger) in posed facial behavior under well-controlled...

Evaluation of Gabor-wavelet-based facial action unit recognition in image sequences of increasing complexity (2002)

Ying-li Tian, Takeo Kanade, Jeffrey F. Cohn

Previous work suggests that Gabor-wavelet-based methods can achieve high sensitivity and specificity for emotionspecified expressions (e.g., happy, sad) and single action units (AUs) of the Facial...

c ○ 2004 Kluwer Academic Publishers. Manufactured in The Netherlands. Object Detection Using the Statistics of Parts (2001)

Henry Schneiderman, Takeo Kanade

Abstract. In this paper we describe a trainable object detector and its instantiations for detecting faces and cars at any size, location, and pose. To cope with variation in object orientation, the...

T.: A hierarchical markov random field model for figureground segregation (2001)

Stella X. Yu, Tai Sing Lee, Takeo Kanade

Abstract. To segregate overlapping objects into depth layers requires the integration of local occlusion cues distributed over the entire image into a global percept. We propose to model this process...

A fundamental theorem of stereo (2001)

Simon Baker, Terence Sim, Takeo Kanade

The complete set of measurements that could ever be used by a passive 3D vision algorithm is the plenoptic function or light-field. We give a concise characterization of when the light-field of a...

A characterization of inherent stereo ambiguities (2001)

Simon Baker, Terence Sim, Takeo Kanade

The complete set of measurements that could ever be used by a stereo algorithm is the plenoptic function or lightfield. We give a concise characterization of when the lightfield of a Lambertian scene...

Bayesian Color Constancy for Outdoor Object Recognition (2001)

Yanghai Tsin, Robert T. Collins, Visvanathan Ramesh, Takeo Kanade

Outdoor scene classification is challenging due to irregular geometry, uncontrolled illumination, and noisy reflectance distributions. This paper discusses a Bayesian approach to classifying a color...

A Comparative Study of Alternative FACS Coding Algorithms (2001)

Jeffrey Cohn Takeo, Jeffrey F. Cohn, Takeo Kanade, Tsuyoshi Moriyama, Zara Ambadar, Jing Xiao, ...

This report describes the results of automated facial expression analysis by the CMU/Pittsburgh group. An interdisciplinary team of consultants, who have combined expertise in computer vision and in...

Chapter 1 SUPER-RESOLUTION: LIMITS AND BEYOND (2001)

Simon Baker, Takeo Kanade

A variety of super-resolution algorithms have been described in this book. Most of them are based on the same source of information however; that the super-resolution image should generate the lower...

A fundamental theorem of stereo (2001)

Simon Baker, Terence Sim, Takeo Kanade

The complete set of measurements that could ever be used by a passive 3D vision algorithm is the plenoptic function or light-field. We give a concise characterization of when the light-field of a...

Gauge Fixing for Accurate 3D Estimation (2001)

Daniel Morris, Kenichi Kanatani, Takeo Kanade

Computer vision techniques can estimate 3D shape from images, but usually only up to a scale factor. The scale factor must be obtained by a physical measurement of the scene or the camera motion....

A Subspace Approach to Layer Extraction, Patch-Based SFM, and Video Compression (2001)

Qifa Ke, Takeo Kanade

Representing videos with layers has important applications such as video compression, motion analysis, 3D modeling and rendering. This thesis proposes a subspace approach to extracting layers from...

Recognizing action units for facial expression analysis (2001)

Ying-li Tian, Takeo Kanade, Jeffrey F. Cohn

Most automatic expression analysis systems attempt to recognize a small set of prototypic expressions (e.g. happiness and anger). Such prototypic expressions, however, occur infrequently. Human...

Carlo EM for data association and its applications in computer vision (2001)

Frank Dellaert, Charles E. Thorpe, Sebastian Thrun, Takeo Kanade, Richard Szeliski

Estimating geometry from images is at the core of many computer vision applications, whether it concerns the imaging geometry, the geometry of the scene, or both. Examples include image mosaicking,...

Appearance Patterns Gabor wavelet (2001)

Ying-li Tian, Takeo Kanade, Jeffrey F. Cohn

In facial expression analysis, two principle approaches to extract facial features are geometric feature-based methods and appearance-based methods such as Gabor filters. In this paper, we combine...

Recognizing Action Units for (2001)

Facial Expression Analysis, Ying-li Tian, Takeo Kanade, Jeffrey F. Cohn

this paper, we develop an Automatic Face Analysis (AFA) system to analyze facial expressions based on both permanent facial features (brows, eyes, mouth) and transient facial features (deepening of...

Multiple Motion Scene Reconstruction from Uncalibrated Views (2001)

Mei Han, Takeo Kanade

We describe a reconstruction method of multiple motion scenes, which are the scenes containing multiple moving objects, from uncalibrated views. Assuming that the objects are moving with constant...

Autonomous Planetary Rover at Carnegie Mellon (2000)

Whittaker, William, Kanade, Takeo, Mitchell, Tom

This report describes progress in research on a six-legged autonomous robot, called the Ambler, designed for planetary exploration. Much of the research focused on understanding the capabilities of...

Eye-state action unit detection by gabor wavelets (2000)

Ying-li Tian, Takeo Kanade, Jeffrey F. Cohn

Abstract Eyes play important roles in emotion and paralinguistic communications. Detection of eye state is necessaryfor applications such as driver awareness systems. In this paper, we develop an...

Hallucinating faces (2000)

Simon Baker, Takeo Kanade

In most surveillance scenarios there is a large distance between the camera and the objects of interest in the scene. Surveillance cameras are also usually set up with wide elds of view in order to...

Shape and motion carving in 6D (2000)

Sundar Vedula, Simon Baker, Steven Seitz, Takeo Kanade

The motion of a non-rigid scene over time imposes more constraints on its structure than those derived from images at a single time instant alone. An algorithm is presented for simultaneously...

Shape and motion carving in 6D (2000)

Sundar Vedula, Simon Baker, Steven Seitz, Takeo Kanade

The motion of a non-rigid scene over time imposes more constraints on its structure than those derived from images at a single time instant alone. An algorithm is presented for simultaneously...

Modifying soft tissue models: Progressive cutting with minimal new element creation (2000)

Andrew B. Mor, Takeo Kanade

Abstract. Surgical simulation is a promising technology for training medical students and planning procedures. One major requirement for these simulation systems is a method to generate realistic...

Scene reconstruction from multiple uncalibrated views (2000)

Mei Han, Takeo Kanade

We describe a factorization-based method to reconstruct Euclidean shape and motion from multiple perspective views with uncalibrated cameras. The method first performs a projective reconstruction...

Shape and Motion Carving in 6D (2000)

Sundar Vedula, Simon Baker, Steven Seitz, Takeo Kanade

The motion of a non-rigid scene over time imposes more constraints on its structure than those derived from images at a single time instant alone. An algorithm is presented for simultaneously...

Reconstruction of a Scene with Multiple Linearly Moving Objects (2000)

Mei Han Takeo, Mei Han, Takeo Kanade

We describe an algorithm for reconstructing a scene containing multiple moving objects. Given a monocular image sequence, we recover the scene structure, the trajectories of the moving objects and...

Image-Consistent Surface Triangulation (2000)

Daniel D. Morris, Takeo Kanade

Given a set of 3D points that we know lie on the surface of an object, we can define many possible surfaces that pass through all of these points. Even when we consider only surface triangulations,...

Shape and Motion Carving in 6D (2000)

Sundar Vedula Simon, Simon Baker, Steven Seitz, Takeo Kanade

The motion of a non-rigid scene over time imposes more constraints on its structure than those derived from images at a single time instant alone. An algorithm is presented for simultaneously...

Limits on Super-Resolution and How to Break Them (2000)

Simon Baker And, Simon Baker, Takeo Kanade

We analyze the super-resolution reconstruction constraints. In particular, we derive a sequence of results which all show that the constraints provide far less useful information as the magnification...

Shape and Motion Carving in 6D (2000)

Sundar Vedula, Simon Baker, Steven Seitz, Takeo Kanade

The motion of a non-rigid scene over time imposes more constraints on its structure than those derived from images at a single time instant alone. An algorithm is presented for simultaneously...

Hallucinating Faces (2000)

Simon Baker, Takeo Kanade

Faces often appear very small in surveillance imagery because of the wide fields of view that are typically used and the relatively large distance between the cameras and the scene. For tasks such as...

Hallucinating Faces (2000)

Simon Baker And, Simon Baker, Takeo Kanade

Faces often appear very small in surveillance imagery because of the wide fields of view that are typically used and the relatively large distance between the cameras and the scene. For tasks such as...

Limits on Super-Resolution and How to Break Them (2000)

Simon Baker, Takeo Kanade

We analyze the super-resolution reconstruction constraints. In particular, we derive a sequence of results which all show that the constraints provide far less useful information as the magnification...

Robust Lip Tracking by Combining Shape, Color and Motion (2000)

Ying-li Tian, Takeo Kanade, Jeffrey F. Cohn

Accurately tracking facial features requires coping with the large variation in appearance across subjects and the combination of rigid and non-rigid motion. In this paper, we describe our work...

Comprehensive Database for Facial Expression Analysis (2000)

Takeo Kanade, Jeffrey F. Cohn, Yingli Tian

Within the past decade, significant effort has occurred in developing methods of facial expression analysis. Because most investigators have used relatively limited data sets, the generalizability of...

Recognizing Lower Face Action Units for Facial Expression Analysis (2000)

Ying-li Tian, Takeo Kanade, Jeffrey F. Cohn

Most automatic expression analysis systems attempt to recognize a small set of prototypic expressions (e.g. happiness and anger). Such prototypic expressions, however, occur infrequently. Human...

A system for video surveillance and monitoring (2000)

Robert T. Collins, Alan J. Lipton, Takeo Kanade, Hironobu Fujiyoshi, David Duggins, Yanghai Tsin, ...

Under the three-year Video Surveillance and Monitoring (VSAM) project (1997–1999), the

3D Model Accuracy and Gauge Fixing CMU-RI-TR-00-32 (2000)

Daniel D. Morris, Kenichi Kanatani, Takeo Kanade

In computer vision we often estimate a 3D model of an object, and its uncertainty, up to an unknown scale factor. This unknown scale factor means that we cannot directly infer positions and lengths...

Modifying soft tissue models: Progressive cutting with minimal new element creation (2000)

Andrew B. Mor, Takeo Kanade

Abstract. Surgical simulation is a promising technology for training medical students and planning procedures. One major requirement for these simulation systems is a method to generate realistic...

Reconstruction of a scene with multiple linearly moving objects (2000)

Mei Han, Takeo Kanade

We describe an algorithm for reconstructing a scene containing multiple moving objects. Given a monocular image sequence, we recover the scene structure, the trajectories of the moving objects and...

Attitude control optimization for a small-scale unmanned helicopter (2000)

Bernard Mettler, Takeo Kanade, Mark B. Tischler, William Messner

Abstract: This paper presents results from the attitude control optimization for a small-scale helicopter by using an identified model of the vehicle dynamics that explicitly accounts for the coupled...

Dual-state parametric eye tracking (2000)

Ying-li Tian, Takeo Kanade, Jeffrey F. Cohn

Most eye trackers work well for open eyes. However, blinking is a physiological necessity for humans. Moreover, for applications such as facial expression analysis and driver awareness systems, we...

Incorporation of Audio in Virtualized Reality (2000)

Saurabh Gupta, Sundar Vedula, Takeo Kanade

Virtualized Reality ™ is a visual medium that allows the user to view a scene from any viewpoint – independent of the physical limitations imposed on the cameras capturing the scene. However the...

System identification modeling of a model-scale helicopter (2000)

Bernard Mettler, Takeo Kanade, Mark B. Tischler

Abstract: Development of a reliable high-performance helicopter-based unmanned aerial vehicle (UAV) requires an accurate and practical model of the vehicle dynamics. This report describes the process...

Scene reconstruction from multiple uncalibrated views (2000)

Mei Han, Takeo Kanade

We describe a factorization-based method to reconstruct Euclidean shape and motion from multiple perspective views with uncalibrated cameras. The method rst performs a projective reconstruction using...

Recognizing Lower Face Action Units for Facial Expression Analysis (2000)

Ying-li Tian, Takeo Kanade, Jeffrey F. Cohn

Most automatic expression analysis systems attempt to recognize a small set of prototypic expressions (e.g. happiness and anger). Such prototypic expressions, however, occur infrequently. Human...

A cooperative algorithm for stereo matching and occlusion detection (2000)

C. Lawrence Zitnick, Takeo Kanade

AbstractÐThis paper presents a stereo algorithm for obtaining disparity maps with occlusion explicitly detected. To produce smooth and detailed disparity maps, two assumptions that were originally...

Probabilistic Registration of 3-D Medical Images (1999)

Mei Chen, Takeo Kanade, Dean Pomerleau, Jeff Schneider

The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the U.S. government....

3d voxel construction based on epipolar geometry (1999)

Makoto Kimura, Hideo Saito, Takeo Kanade

In this paper, we propose an approach for construction of a projective 3D voxel space based on epipolar geometry obtained with weak calibration. This concept of voxel space defines the epipolar lines...

System identification of small-size unmanned helicopter dynamics (1999)

Bernard Mettler, Mark B. Tischler, Takeo Kanade

Abstmcf: Flight testing of a fully-instrumented model-scale unmanned helicopter (Yamaha R-SO with loft. diameter rotor) was conducted for the purpose of dynamic model identification. This paper...

A VLSI Sorting Image Sensor: Global Massively Parallel Intensity-to-Time Processing for Low-Latency, Adaptive Vision (1999)

Vladimir Brajovic, Takeo Kanade

Abstract—This paper presents a new intensity-to-time processing paradigm suitable for very large scale integration (VLSI) computational sensor implementation of global operations over sensed...

Anomaly detection through registration (1999)

Mei Chen, Takeo Kanade, Henry A. Rowley, Dean Pomerleau

The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the U.S. government....

Hallucinating Faces (1999)

Simon Baker, Takeo Kanade

In most surveillance scenarios there is a large distance between the camera and the objects of interest in the scene. Surveillance cameras are also usually set up with wide fields of view in order to...

Super-resolution optical flow (1999)

Simon Baker, Takeo Kanade

Existing approaches to super-resolution are not applicable to videos of faces because faces are non-planar, non-rigid, non-lambertian, and are subject to self occlusion. We present super-resolution...

Uncertainty Modeling for Optimal Structure from Motion (1999)

Daniel Morris Kenichi, Daniel D. Morris, Kenichi Kanatani, Takeo Kanade

. The parameters estimated by Structure from Motion (SFM) contain inherent indeterminacies which we call gauge freedoms. Under a perspective camera, shape and motion parameters are only recovered up...

Automated Face Analysis by Feature Point Tracking Has High Concurrent Validity with Manual FACS Coding (1999)

Jeffrey F. Cohn, Adena J. Zlochower, James Lien, Takeo Kanade, Automated Face Analysis

The face is a rich source of information about human behavior. Available methods for coding facial displays, however, are human-observer dependent, labor intensive, and difficult to standardize. To...

Recognizing Action Units for Facial Expression Analysis (1999)

Ying-li Tian, Takeo Kanade, Jeffrey F. Cohn

Most automatic expression analysis systems attempt to recognize a small set of prototypic expressions (e.g. happiness and anger). Such prototypic expressions, however, occur infrequently. Human...

Hallucinating Faces (1999)

Simon Baker, Takeo Kanade

In most surveillance scenarios there is a large distance between the camera and the objects of interest in the scene. Surveillance cameras are also usually set up with wide fields of view in order to...

Uncertainty Modeling for Optimal Structure from Motion (1999)

Daniel D. Morris, Kenichi Kanatani, Takeo Kanade

. The parameters estimated by Structure from Motion (SFM) contain inherent indeterminacies which we call gauge freedoms. Under a perspective camera, shape and motion parameters are only recovered up...

Dual-State Parametric Eye Tracking (1999)

Ying-li Tian, Takeo Kanade, Jeffrey F. Cohn

Most eye trackers work well for open eyes. However, blinking is a physiological necessity for humans. Moreover, for applications such as facial expression analysis and driver awareness systems, we...

A System for Video Surveillance and Monitoring (1999)

Robert T. Collins, Alan J. Lipton, Takeo Kanade

The Robotics Institute at Carnegie Mellon University (CMU) and the Sarnoff Corporation are developing a system for autonomous Video Surveillance and Monitoring. The technical objective is to use...

Appearance-Based Virtual View Generation of Temporally-Varying Events from Multi-Camera Images in the 3D Room (1999)

Hideo Saito, Shigeyuki Baba, Makoto Kimura, Sundar Vedula, Takeo Kanade

In this paper, we present an "appearance-based" virtual view generation method for temporally-varying events taken by multiple cameras of the "3D Room", developed by our group....

Forward Modeling of Ultrasound Propagation in Layered Medium (1999)

Joyoni Dey, Takeo Kanade

this report we discuss some general applicability, the advantages and limitations of the model in more detail. 1.3 Contents

Probabilistic Registration of 3-D Medical Images (1999)

Mei Chen, Takeo Kanade, Dean Pomerleau, Jeff Schneider

Registration between 3-D images of human anatomies enables cross-subject diagnosis. However, innate differences in the appearance and location of anatomical structures between individuals make...

Uncertainty Modeling for Optimal Structure from Motion (1999)

Daniel D. Morris, Kenichi Kanatani, Takeo Kanade

The parameters estimated by Structure from Motion contain inherent indeterminacies. In particular, shape and motion parameters are only recovered up to a similarity transformation. Past work on...

Three-Dimensional Scene Flow (1999)

Sundar Vedula, Simon Baker, Peter Rander, Robert Collins, Takeo Kanade

Scene flow is the three-dimensional motion field of points in the world, just as optical flow is the twodimensional motion field of points in an image. Any optical flow is simply the projection of...

Three-Dimensional Scene Flow (1999)

Sundar Vedula Simon, Simon Baker, Peter Rander, Robert Collins, Takeo Kanade

Scene flow is the three-dimensional motion field of points in the world, just as optical flow is the twodimensional motion field of points in an image. Any optical flow is simply the projection of...

A Cooperative Algorithm for Stereo Matching and Occlusion Detection (1999)

C. Lawrence Zitnick, Takeo Kanade, States Government

This paper presents a stereo algorithm for obtaining disparity maps with occlusion explicitly detected. To produce smooth and detailed disparity maps, two assumptions that were originally proposed by...

The Factorization Method with Linear Motions (1999)

Mei Han Takeo, Mei Han, Takeo Kanade

In this paper we describe the factorization method with linear motions. We design an unified representation of scene structure and moving objects by assuming that the objects are moving linearly and...

Perspective Factorization Methods for Euclidean Reconstruction (1999)

Mei Han, Takeo Kanade

In this paper we describe a factorization-based method for Euclidean reconstruction with a perspective camera model. It iteratively recovers shape and motion by weak perspective factorization method...

Multi-State Based Facial Feature Tracking and Detection (1999)

Ying-li Tian, Takeo Kanade, Jeffrey F. Cohn

Accurately and robustly tracking facial features must cope with the large variation in appearance across subjects and the combination of rigid and non-rigid motion. We present a work toward a robust...

Name-It: Naming and Detecting Faces in News Video (1999)

Shin'ichi Satoh, Toshio Sato, Michael A. Smith, Takeo Kanade

We have developed Name-It, a system that associates faces and names in news videos. The system is given news videos, which include image sequences and transcripts obtained from audio tracks or closed...

Shape Reconstruction in Projective Grid Space from Large Number of Images (1999)

Hideo Saito, Takeo Kanade

This paper proposes a new scheme for multi-image projective reconstruction based on a projective grid space. The projective grid space is defined by two basis views and the fundamental matrix...

Appearance-based virtual view generation of temporallyvarying events from multi-camera images in the 3d room (1999)

Hideo Saito, Shigeyuki Baba, Makoto Kimura, Sundar Vedula, Takeo Kanade

In this paper, we present an “appearance-based ” virtual view generation method for temporally-varying events taken by multiple cameras of the “3D Room”, developed by our group. With this...

A video-rate stereo machine and its application to virtual reality (1999)

Kazuo Oda, Masaya Tanaka, Atsushi Yoshida, Hiroshi Kano, Takeo Kanade

Stereo range imaging uses correspondence between sets of two or more images for depth measurement. Despite a great deal of research during the past two decades, no stereo systems developed so far...

Probabilistic Registration of 3-D Medical Images (1999)

Mei Chen, Takeo Kanade, Dean Pomerleau, Jeff Schneider

The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the U.S. government....

Appearance-based virtual view generation of temporallyvarying events from multi-camera images in the 3d room (1999)

Hideo Saito, Shigeyuki Baba, Makoto Kimura, Sundar Vedula, Takeo Kanade

In this paper, we present an “appearance-based ” virtual view generation method for temporally-varying events taken by multiple cameras of the “3D Room”, developed by our group. With this...

A video-rate stereo machine and its application to virtual reality (1999)

Kazuo Oda, Masaya Tanaka, Atsushi Yoshida, Hiroshi Kano, Takeo Kanade

Stereo range imaging uses correspondence between sets of two or more images for depth measurement. Despite a great deal of research during the past two decades, no stereo systems developed so far...

Appearance-Based Virtual View Generation of Temporally-Varying Events from Multi-Camera Images in the 3D Room (1999)

Hideo Saito, Shigeyuki Baba, Makoto Kimura, Sundar Vedula, Takeo Kanade

In this paper, we present an "appearance-based" virtual view generation method for temporally-varying events taken by multiple cameras of the "3D Room", developed by our group....

Appearance-Based Virtual View Generation of Temporally-Varying Events (1999)

Hideo Saito, Shigeyuki Baba, Makoto Kimura, Sundar Vedula, Takeo Kanade

In this paper, we present an "appearance-based" virtual view generation method for temporally-varying events taken by multiple cameras of the "3D Room", developed by our group....

Video OCR: Indexing Digital News Libraries by Recognition of Superimposed Captions (1999)

Toshio Sato Takeo, Toshio Sato, Takeo Kanade, Ellen K. Hughes, Michael A. Smith

. The automatic extraction and recognition of news captions and annotations can be of great help locating topics of interest in digital news video libraries. To achieve this goal, we present a...

The Factorization Method with Linear Motions (1999)

Mei Han, Takeo Kanade

In this paper we describe the factorization method with linear motions. We design an uni ed representation of scene structure and moving objects by assuming that the objects are moving linearly and...

Perspective factorization methods for Euclidean reconstruction (1999)

Mei Han, Takeo Kanade

In this paper we describe a factorization-based method for Euclidean reconstruction with a perspective camera model. It iteratively recovers shape and motion by weak perspective factorization method...

3-D deformable registration of medical images using a statistical atlas (1999)

Mei Chen, Takeo Kanade, Dean Pomerleau, Jeff Schneider

The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the U.S. government....

Computer Image Processing”. (1999)

Ying-li Tian, Takeo Kanade, Jeffrey F. Cohn

Accurately and robustly tracking facial features must cope with the large variation in appearance across subjects and the combination of rigid and non-rigid motion. We present a work toward a robust...

Uncertainty modeling for optimal structure from motion (1999)

Daniel D. Morris, Kenichi Kanatani, Takeo Kanade

Abstract. The parameters estimated by Structure from Motion (SFM) contain inherent indeterminacies which we call gauge freedoms. Under a perspective camera, shape and motion parameters are only...

3-D deformable registration of medical images using a statistical atlas (1999)

Mei Chen, Takeo Kanade, Dean Pomerleau, Jeff Schneider

Registration between 3-D images of human anatomies enables cross-subject diagnosis. However, innate differences in the appearance and location of anatomical structures between individuals make...

Super-resolution optical flow (1999)

Simon Baker, Takeo Kanade

Existing approaches to super-resolution are not applicable to videos of faces because faces are non-planar, non-rigid, non-lambertian, and are subject to self occlusion. We present super-resolution...

A video-rate stereo machine and its application to virtual reality (1999)

Kazuo Oda, Masaya Tanaka, Atsushi Yoshida, Hiroshi Kano, Takeo Kanade

Stereo range imaging uses correspondence between sets of two or more images for depth measurement. Despite a great deal of research during the past two decades, no stereo systems developed so far...

Anomaly detection through registration (1999)

Mei Chen, Takeo Kanade, Henry A. Rowley, Dean Pomerleau

The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the U.S. government....

Anomaly detection through registration (1999)

Mei Chen, Takeo Kanade, Dean Pomerleau, Henry A. Rowley

We study an application of image registration in the medical domain. Based on a 3-D hierarchical deformable registration algorithm, we developed a prototype for automatic registering a standard atlas...

Anomaly detection through registration (1999)

Mei Chen, Takeo Kanade, Henry A. Rowley, Dean Pomerleau

We study an application of image registration in the medical domain. Based on a 3-D hierarchical deformable registration algorithm, we have developed a prototype system which automatically aligns a...

Appearance-based virtual view generation of temporallyvarying events from multi-camera images in the 3d room (1999)

Hideo Saito, Shigeyuki Baba, Makoto Kimura, Sundar Vedula, Takeo Kanade

In this paper, we present an “appearance-based ” virtual view generation method for temporally-varying events taken by multiple cameras of the “3D Room”, developed by our group. With this...

Anomaly detection through registration (1999)

Mei Chen, Takeo Kanade, Henry A. Rowley, Dean Pomerleau

We study an application of image registration in the medical domain. Based on a 3-D hierarchical deformable registration algorithm, we have developed a prototype system which automatically aligns a...

3-D deformable registration of medical images using a statistical atlas (1999)

Mei Chen, Takeo Kanade, Dean Pomerleau, Jeff Schneider

Registration between 3-D images of human anatomies enables cross-subject diagnosis. However, innate differences in the appearance and location of anatomical structures between individuals make...

Anomaly Detection through Registration (1999)

Mei Chen, Takeo Kanade, Dean Pomerleau, Henry A. Rowley

We study an application of image registration in the medical domain. Based on a 3-D hierarchical deformable registration algorithm, we developed a prototype for automatic registering a standard atlas...

Shock Graphs and Shape Matching (1999)

Takeo Kanade, Olivier Faugeras

Upon entering a room, one first notices the presence of a particular object, such as a dog, before

Volumetric deformation analysis using mechanics-based data fusion: Applications in cardiac motion recovery (1999)

Pengcheng Shi, Albert J. Sinusas, R. Todd Constable, James S. Duncan, Takeo Kanade, Olivier Faugeras

Abstract. Non–rigid motion estimation from image sequences is essential in analyzing and understanding the dynamic behaviors of physical objects. One important example is the dense field motion...

Control of a Direct-Drive Arm, (1998)

Asada,Haruhiko, Kanade,Takeo, Takeyama,Ichiro

A direct-drive arm is a new mechanical arm in which the shafts of articulated joints are directly coupled to the rotors of high performance torque motors. Since the arm does not contain any gears or...

Appropriate Lengths between Phalanges of Multijointed Fingers for Stable Grasping. (1998)

Okada,Tokuji, Kanade,Takeo

An appropriate arrangement of finger joints is very important since the stability of grasping an object greatly depends on that arrangement. Multijointed fingers can grasp an object with many points...

1986 Year End Report for Road Following at Carnegie-Mellon. (1998)

Thorpe,Charles, Kanade,Takeo

This report describes progress in vision and navigation for outdoor mobile robots at the Carnegie Mellon Robotics Institute during 1986. This research was sponsored by DARPA as part of the Strategic...

End of Year Report for Parallel Vision Algorithm Design and Implementation. (1998)

Kanade,Takeo, Webb,Jon A.

The parallel vision algorithm design and implementation project was established to facilitate vision programming on parallel architectures, particularly low-level vision and robot vehicle control...

Multi-Disciplinary Techniques for Understanding Time-Varying Space-Based Imagery. (1998)

Casasent, David, Sanderson, Arthur, Kanade, Takeo

This project is intended to combine: pattern recognition, image understanding and artificial intelligence techniques for space-based image processing as well as: optical and digital processing...

Multi-Disciplinary Techniques for Understanding Time-Varying Space-Based Imagery. (1998)

Casasent, David, Sanderson, Arthur, Kanade, Takeo, Vijaya Kumar, B. V.

This project combined pattern recognition, image understanding and artificial intelligence techniques for space-based image processing. A special feature of this effort is the attempt to use both...

Kalman Filter-Based Algorithms for Estimating Depth from Image Sequences. (1998)

Matthies, Larry, Szeliski, Richard, Kanade, Takeo

Using known camera motion to estimate depth from image sequences is important in robotics applications such as navigation and manipulation. For many applications, having an on-line, incremental...

Model-Based Vision System by Object-Oriented Programming. (1998)

Chang, Huey, Ikeuchi, Katsushi, Kanade, Takeo

This paper presents an approach to using object-oriented programming for the generation of a object recognition program that recognizes a complex 3-D object within a jumbled pile. We generate a...

End of Year Report for Parallel Vision Algorithm Design and Implementation. (1998)

Kanade, Takeo, Webb, Jon A.

Progress on the Parallel Vision project is reported. Three major accomplishments are noted: the development of the Apply language, the WEB library, and benchmarks of Warp for the DARPA image...

3-D Vision Techniques for Autonomous Vehicles. (1998)

Hebert, Martial, Kanade, Takeo, Kweon, Inso

A Mobile robot needs an internal representation of its environment in order to accomplish its mission. Building such a representation involves transforming raw data from sensors into a meaningful...

1987 Year End Report for Road Following at Carnegie Mellon. (1998)

Thorpe, Charles E., Kanade, Takeo

This report describes progress in vision and navigation for outdoor mobile robots at the Carnegie Mellon Robotics Institute during 1987. This research centers on guiding outdoor autonomous vehicles....

Surface Reflection: Physical and Geometrical Perspectives. (1998)

Nayar, Shree K., Ikeuchi, Katsushi, Kanade, Takeo

Machine vision can greatly benefit from the development of accurate reflectance models. There are two approaches to the study of reflection: physical and geometrical optics. While geometrical models...

1988 Year End Report for Road Following at Carnegie Mellon. (1998)

Thorpe, Charles, Kanade, Takeo

This report describes the progress in vision and navigation for outdoor mobile robots at the Carnegie Mellon Robotics Institute during 1988. This research was primarily sponsored by DARPA as part of...

Parallel Vision Algorithm Design and Implementation 1988 End of Year Report. (1998)

Kanade, Takeo, Webb, Jon A.

The Apply programming language has been extended to allow variable-sized image computations, and also to allow border mirroring, in which pixels accessed outside the borders are produced by copying...

Year End Report: Autonomous Planetary Rover at Carnegie Mellon, 1989. (1998)

Whittaker, William, Kanade, Takeo, Mitchell, Tom

The Carnegie Mellon University program to develop an Earth-based prototype of an autonomous planetary rover is organized around three teams that are developing the locomotion, perception, and...

Shape from Interreflections. (1998)

Nayar, Shree K., Ikeuchi, Katsushi, Kanade, Takeo

All shape-from-intensity methods assume that points in a scene are only illuminated by sources of light. Most scenes consist of concave surfaces and/or concavities that result from multiple objects...

Perception for Outdoor Navigation. (1998)

Thorpe, Charles, Kanade, Takeo

Research supported by this contract includes perception for road following, terrain mapping for off-road navigation, and systems software for building integrated mobile robots. We overview our...

Perception for Outdoor Navigation. First Year Report. (1998)

Thorpe, Charles, Kanade, Takeo

Research supported by this contract includes perception for road following, terrain mapping for off-road navigation, and systems software for building integrated mobile robots. We overview our...

Adaptive Control of Space Robot System with an Attitude Controlled Base, (1998)

Xu, Yangsheng, Shum, Heung-Yeung, Lee, Ju-Jang, Kanade, Takeo

In this report, we discuss adaptive control of a space robot system with an attitude controlled base on which the robot is attached. We at first derive the system kinematic and dynamic equations...

Perception for Outdoor Navigation. (1998)

Thorpe, Charles, Kanade, Takeo

The contract made significant progress across a broad front on the problems of computer vision for outdoor mobile robots. New algorithms were built in neural networks, range data analysis, object...

A Paraperspective Factorization Method for Shape and Motion Recovery, (1998)

Poelman, Conrad J., Kanade, Takeo

In this paper, we present a method for recovering both the shape of an object and its motion relative to the camera from a sequence of images of the object, using feature points tracked throughout...

Experiments in Multiple-Baseline Stereo. (1998)

Nakahara, Tomoharu, Kanade, Takeo

This paper presents the results of our experiments with a unique multiple-baseline stereo technique. This algorithm for producing precise, unambiguous depth maps from a set of multiple stereo pairs...

Uncertainty in Object Pose Determination with Three Light-Stripe Range Measurements, (1998)

Kemmotsu, Keiichi, Kanade, Takeo

The pose (position and orientation) of a polyhedral object can be determined with sparse range data obtained from simple light-stripe range finders. However, the sensing data inherently contains some...

Real-Time 3-D Pose Estimation Using A High-Speed Range Sensor. (1998)

Simon, David A., Hebert, Martial, Kanade, Takeo

This report describes a system which can perform full 3-D pose estimation of a single arbitrarily shaped, rigid object at rates up to 10Hz. A triangular mesh model of the object to be tracked is...

Digit-Eyes: Vision-Based Human Hand Tracking. (1998)

Rehg, James M., Kanade, Takeo

Passive sensing of human hand and limb motion is important for a wide range of applications from human-computer interaction to athletic performance measurement. High degree of freedom articulated...

Visual Tracking of Self-Occluding Articulated Objects. (1998)

Rehg, James R., Kanade, Takeo

Computer sensing of hand and limb motion is an important problem for applications in human-computer interaction, virtual reality, and athletic performance measurement. We describe a framework for...

A Multi-Body Factorization Method for Motion Analysis, (1998)

Costeira, Joao, Kanade, Takeo

The structure-from-motion problem has been extensively studied in the field of computer vision. Yet, the bulk of the existing work assumes that the scene contains only a single moving object. The...

Video Skimming and Characterization through the Combination of Image and Language Understanding Techniques (1998)

Smith, Michael A., Kanade, Takeo

Digital video is rapidly becoming important for education, entertainment, and a host of multimedia applications. With the size of the video collections growing to thousands of hours, technology is...

A Tracker for Broken and Closely-Spaced Lines (1998)

Chiba, Naoki, Kanade, Takeo

We propose an automatic line tracking method which can deal with broken or closely-spaced line segments more accurately than previous methods over an image sequence. The method uses both grey scale...

Rotation Invariant Neural Network-Based Face Detection (1998)

Rowley, Henry A., Baluja, Shumeet, Kanade, Takeo

In this paper, we present a neural network-based face detection system. Unlike similar systems which are limited to detecting upright, frontal faces, this system detects faces at any degree of...

Unmanned Ground Vehicle System Perception for Outdoor Navigation. (1998)

Thorpe, Charles, Hebert, Martial, Pomerleau, Dean, Stentz, Anthony, Kanade, Takeo

This research includes perception for road following and cross-country navigation, path planning, and tools for building integrated mobile robot systems. Main accomplishments, software components,...

Appearance-Based Virtual View Generation of Temporally-Varying Events from Multi-Camera Images in the 3D Room (1998)

Salto, Hideo, Baba, Shigeyuki, Kimura, Makoto, Vedula, Sundar, Kanade, Takeo

In this paper, we present an "appearance-based" virtual view generation method for temporally-varying events taken by multiple cameras of the "3D Room", developed by our group. With this method, we...

A System for Video Surveillance and Monitoring CMU VSAM Final Report (1998)

Kanade, Takeo, Collins, Robert T., Lipton, Alan J., Fujiyoshi, Hironobu, Duggins, David

Under the three-year Video Surveillance and Monitoring (VSAM) project, the Robotics Institute at Carnegie Mellon University (CMU) and the Sarnoff Corporation have developed a system for autonomous...

Basic Research in Computer Science: Image Understanding (1998)

Kanade, Takeo, Shafer, Steven, Ikeuchi, Katsushi

The CMU Image Understanding program performed basic research and technology development toward robust, flexible, and precise vision systems to impact a wide variety of military and civilian...

Simulating surgery using volumetric object representations, real-time volumerendering, and haptic feedback. Medical Image Analysis (1998)

Sarah Gibson, Christina Fyock, Eric Grimson, Takeo Kanade, Ron Kikinis, Hugh Lauer, ...

Surgical simulation has many applications in education and training, surgical planning, and intra-operative assistance. However, extending current surface-based computer graphics methods to model...

Neural Network-Based Face Detection (1998)

Henry A. Rowley, Student Member, Shumeet Baluja, Takeo Kanade

Abstract—We present a neural network-based upright frontal face detection system. A retinally connected neural network examines small windows of an image and decides whether each window contains a...

Rotation invariant neural network-based face detection (1998)

Henry A. Rowley, Shumeet Baluja, Takeo Kanade

In this paper, we present a neural network-based face detection system. Unlike similar systems which are limited to detecting upright, frontal faces, this system detects faces at any degree of...

A multibody factorization method for independently moving objects (1998)

Joiio Costeira, Takeo Kanade, Mutin Analysis Invariants

he structure-from-motion problem has been extensively studied in the field of computer vision. Yet, the bulk of the existing work assumes that the scene contains only a single moving object. The more...

Computational model of image formation process in DIC microscopy (1998)

Farhana Kagaiwalaa, Takeo Kanade

A computational model of the image formation process has been developed for the Nomarski differential interference contrast (DIC) microscope. The DIC microscope images variations of the phase of the...

Computational sensor for visual tracking with attention (1998)

Vladimir Brajovic, Takeo Kanade

Abstract — This paper presents a VLSI embodiment of an optical tracking computational sensor which focuses attention on a salient target in its field of view. Using both low-latency massive...

Optimal approximation of uniformly rotated images: Relationships between karhunenloeve expansion and discrete cosine transform (1998)

Michihiro Uenohara, Takeo Kanade

Abstract—We will present in this correspondence that for uniformly rotated images, the optimal approximation of the images can be obtained by computing the basis vectors for the discrete cosine...

Content-based 3d neuroradiologic image retrieval: Preliminary results (1998)

Yanxi Liu, Takeo Kanade

conclusions contained in this document are those of the authors and should not be interpreted as necessarily representing

Rotation Invariant Neural Network-Based Face Detection (1998)

Henry A. Rowley, Shumeet Baluja, Takeo Kanade

In this paper, we present a neural network-based face detection system. Unlike similar systems which are limited to detecting upright, frontal faces, this system detects faces at any degree of...

Automated Facial Expression Recognition Based on FACS Action Units (1998)

James Lien, Jeffrey F. Cohn, Takeo Kanade, Ching-chung Li

Automated recognition of facial expression is an important addition to computer vision research because of its relevance to the study of psychological phenomena and the development of human-computer...

Subtly Different Facial Expression Recognition And Expression Intensity Estimation (1998)

Jeffrey F. Cohn, Takeo Kanade, Ching-chung Li

We have developed a computer vision system, including both facial feature extraction and recognition, that automatically discriminates among subtly different facial expressions. Expression...

Homography-Based 3D Scene Analysis of Video Sequences (1998)

Mei Han, Takeo Kanade

We propose a framework to recover projective depth based on image homography and discuss its application to scene analysis of video sequences. We describe a robust homography algorithm which...

A Volumetric Iterative Approach to Stereo Matching and Occlusion Detection (1998)

C. Lawrence Zitnick, Takeo Kanade

This paper presents a stereo algorithm for obtaining disparity maps with explicitly detected occlusion. To produce smooth and detailed disparity maps, two assumptions that were originally proposed by...

Advances in Cooperative Multi-Sensor Video Surveillance (1998)

Takeo Kanade, Robert T. Collins, Alan J. Lipton, Peter Burt, Lambert Wixson

Carnegie Mellon University (CMU) and the Sarnoff Corporation (Sarnoff) are performing an integrated feasibility demonstration of Video Surveillance and Monitoring (VSAM). The objective is to develop...

The 3D Room: Digitizing Time-varying 3D Events by Synchronized Multiple Video Streams (1998)

Takeo Kanade, Hideo Saito, Sundar Vedula

The “3D room ” is a facility for 4D digitization- capturing and modeling a real time-varying event into a computer as 3D representations which depend on time (1D). On the walls and ceiling of the...

A Tracker for Broken and Closely-Spaced Lines (1998)

Naoki Chiba, Takeo Kanade

We propose an automatic line tracking method which can deal with broken or closely-spaced line segments more accurately than previous methods over an image sequence. The method uses both grey scale...

A Tracker For Broken And Closely-Spaced Lines (1998)

Naoki Chiba, Takeo Kanade

We propose an automatic line tracking method which is robust in tracking broken and closely-spaced line segments over an image sequence. The method uses both the grey-level information of original...

Optical Flow Estimation Using Wavelet Motion Model (1998)

Yu-Te Wu, Takeo Kanade, Ching-Chung Li

A motion estimation algorithm using wavelet approximation as an optical #ow model has been developed to estimate accurate dense optical #ow from an image sequence. This wavelet motion model is...

Rotation Invariant Neural Network-Based Face Detection (1998)

Henry Rowley Shumeet, Henry A. Rowley, Shumeet Baluja, Takeo Kanade

In this paper, we present a neural network-based face detection system. Unlike similar systems which are limited to detecting upright, frontal faces, this system detects faces at any degree of...

Quantitative Study of Brain Anatomy (1998)

Mei Chen, Takeo Kanade, Henry A. Rowley, Dean Pomerleau

We introduce a system that automatically segments and classifies features in 3-D images. The system's accuracy is comparable to manual segmentation. It takes 12 minutes to segment and classify...

Rotation Invariant Neural Network-Based Face Detection (1998)

Henry A. Rowley, Shumeet Baluja, Takeo Kanade

In this paper, we present a neural network-based face detection system. Unlike similar systems which are limited to detecting upright, frontal faces, this system detects faces at any degree of...

Video OCR for Digital News Archives (1998)

Toshio Sato, Takeo Kanade, Ellen K. Hughes, Michael A. Smith

Video OCR is a technique that can greatly help to locate topics of interest in a large digital news video archive via the automatic extraction and reading of captions and annotations. News captions...

Optical Flow Estimation Using Wavelet Motion Model (1998)

Yu-te Wu, Takeo Kanade, Ching-Chung Li, Ching-chung Li

A motion estimation algorithm using wavelet approximation as an optical flow model has been developed to estimate accurate dense optical flow from an image sequence. This wavelet motion model is...

Video OCR for Digital News Archives (1998)

Toshio Sato, Takeo Kanade, Ellen K. Hughes, Michael A. Smith

Video OCR is a technique that can greatly help to locate topics of interest in a large digital news video archive via the automatic extraction and reading of captions and annotations. News captions...

A Unified Factorization Algorithm for Points, Line Segments and Planes with Uncertainty Models (1998)

Daniel Morris, Takeo Kanade

In this paper we present a unified factorization algorithm for recovering structure and motion from image sequences by using point features, line segments and planes. This new formulation is based on...

A Fast, Affordable System for Augmented Reality (1998)

David Larose, Dr. Takeo Kanade

: This paper presents a framework for augmented reality. Head tracking is accomplished using a head-mounted camera, which uses an optical flow based algorithm to track patterns on the ceiling. The...

The 3D Room: Digitizing Time-Varying 3D Events by Synchronized Multiple Video Streams (1998)

Takeo Kanade, Hideo Saito, Sundar Vedula

This document describes the current 3D Room as of December 1998 -- design, components and capabilities - built at Robotics Institute, Carnegie Mellon University (CMU).

D.: Quantitative study of brain anatomy (1998)

Mei Chen, Takeo Kanade, Henry A. Rowley, Dean Pomerleau

The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the U.S. government....

3-D Deformable Registration of MedicalImages Using a Statistical Atlas (1998)

Mei Chen, Takeo Kanade, Dean Pomerleau, Jeff Schneider

The views and conclusions contained in this document are those of the authors and shouldnot be interpreted as representing the official policies, either expressed or implied, of the U.S. government....

Factorization methods for structure from motion (1998)

Takeo Kanade, Daniel D. Morris

In this article we present anoverview of factorization methods for recovering structure and motion from image sequences. We distinguish these methods from general non-linear algorithms primarily by...

Simulating surgery using volumetric object representations, real-time volumerendering, and haptic feedback. Medical Image Analysis (1998)

Sarah Frisken Gibson, Samosky Akira Sawada, Sarah Gibson, Christina Fyock, Christina Fyock, ...

Surgical simulation has many applications in education and training, surgical planning, and intraoperative assistance. However, extending current surface-based computer graphics methods to model...

A unified factorization algorithm for points, line segments and planes with uncertainty models (1998)

Daniel D. Morris, Takeo Kanade

In this paper we present a unified factorization algorithm for recovering structure and motion from image sequences by using point features, line segments and planes. This new formulation is based on...

D.: Quantitative study of brain anatomy (1998)

Mei Chen, Takeo Kanade, Henry A. Rowley, Dean Pomerleau

We introduce a system that automatically segments and classifies features in brain MRIs. It takes 22 minutes to segment 144 structures in a 256x256x124 voxel image on an SGI computer with three 194...

A fast, affordable system for augmented reality (1998)

David Larose, Dr. Takeo Kanade

This paper presents a framework for augmented reality. Head tracking is accomplished using a head-mounted camera, which uses an optical flow based algorithm to track patterns on the ceiling. The...

A volumetric iterative approach to stereo matching and occlusion detection (1998)

C. Lawrence Zitnick, Takeo Kanade

Views and conclusions contained in the document are those of the authors and should not be interpreted as necessarily representing official policies or endorsements, either expressed or implied, of...

Content-based 3d neuroradiologic image retrieval: Preliminary results (1998)

Yanxi Liu, Takeo Kanade

Acontent-based 3D neuroradiologic image retrieval system is being developed at the Robotics Institute of CMU. The special characteristics of this system include: 1) directly dealing with multimodal...

Neural Network-Based Face Detection (1998)

Henry A. Rowley, Shumeet Baluja, Takeo Kanade

We present a neural network-based face detection system. A retinally connected neural network examines small windows of an image, and decides whether each window contains a face. The system...

Video OCR for Digital News Archives (1998)

Toshio Sato Takeo, Toshio Sato, Takeo Kanade, Ellen K. Hughes, Michael A. Smith

Video OCR is a technique that can greatly help to locate topics of interest in a large digital news video archive via the automatic extraction and reading of captions and annotations. News captions...

A tracker for broken and closely-spaced lines (1998)

Naoki Chiba, Takeo Kanade

We propose an automatic line tracking method which can deal with broken or closely-spaced line segments more accurately than previous methods over an image sequence. The method uses both grey scale...

D.: Quantitative study of brain anatomy (1998)

Mei Chen, Takeo Kanade, Henry A. Rowley, Dean Pomerleau

We introduce a system that automatically segments and classifies features in brain MRIs. It takes 22 minutes to segment 144 structures in a 256x256x124 voxel image on an SGI computer with three 194...

Volumetric object modeling for surgical simulation (1998)

Randy Osborne, Joseph Samosky, Akira Sawada, Sarah Gibson, Sarah Gibson, Christina Fyock, ...

Surgical simulation has many applications in medical education, surgical training, surgical planning, and intra-operative assistance. However, extending current surface-based computer graphics...

Content-based 3d neuroradiologic image retrieval: Preliminary results (1998)

Yanxi Liu, Takeo Kanade

A content-based 3D neuroradiologic image retrieval system is being developed at the Robotics Institute of CMU. The special characteristics of this system include: 1) directly dealing with multimodal...

Homography-based 3d scene analysis of video sequences (1998)

Mei Han, Takeo Kanade

We propose a framework to recover projective depth based on image homography and discuss its application to scene analysis of video sequences. We describe a robust homography algorithm which...

Rotation invariant neural network-based face detection (1998)

Henry A. Rowley, Shumeet Baluja, Takeo Kanade

In this paper, we present a neural network-based face detection system. Unlike similar systems which are limited to detecting upright, frontal faces, this system detects faces at any degree of...

Simulating surgery using volumetric object representations, real-time volumerendering, and haptic feedback. Medical Image Analysis (1998)

Sarah Gibson, Christina Fyock, Eric Grimson, Takeo Kanade, Ron Kikinis, Hugh Lauer, ...

Surgical simulation has many applications in education and training, surgical planning, and intra-operative assistance. However, extending current surface-based computer graphics methods to model...

A visual/haptic interface to virtual environment (WYSIWYF display) and its application (1998)

Yasuyoshi Yokokohji, Ralph L. Hollis, Takeo Kanade

To build a VR training system for visuomotor skills, an image displayed by a visual interface should be correctly registered to a haptic interface so that the visual sensation and the haptic...

Neural Network-Based Face Detection (1998)

Henry A. Rowley, Shumeet Baluja, Takeo Kanade

We present a neural network-based face detection system. A retinally connected neural network examines small windows of an image, and decides whether each window contains a face. The system...

Perception for Outdoor Navigation. (1997)

Thorpe, Charles, Kanade, Takeo, Hebert, Martial, Pomerleau, Dean

This report reviews progress at Carnegie Mellon from August 16, 1991 to August 15, 1992 on research sponsored by DARPA, DoD, monitored by the U.S. Army Topographic Engineering Center under contract...

CMU Very Fast Range-Imaging System, (1997)

Tada, Shigeyuki, Gruss, Andrew, Kanade, Takeo

We present a high-speed range-imaging system based on a VLSI computational sensor developed in the CMU Computer Science Department. The VLSI range sensor is a custom chip consisting of an array of...

Name-It: Association of Face and Name in Video. (1997)

Satoh, Shin Ichi, Kanade, Takeo

This paper proposes a novel approach to extract meaningful content information from video by collaborative integration of image understanding and natural language processing. As an actual example, we...

Synchronous Capture of Image Sequences from Multiple Cameras. (1997)

Narayanan, P. J., Rander, Peter, Kanade, Takeo

Several applications today need to digitally capture every frame of a video stream or a camera. These range from psychological studies to surveillance to video processing. Some applications also need...

Video-Rate Z Keying: A New Method for Merging Images. (1997)

Kanade, Takeo, Oda, Kazuo, Yoshida, Atsushi, Tanaka, Masaya, Kano, Hiroshi

Video-rate z keying is a new image keying method for merging real and synthetic images in real time. In visual media communication and display, it is often necessary to merge video signals from a...

A sequential factorization method for recovering shape and motion from image streams (1997)

Toshihiko Morita, Takeo Kanade

Abstract—We present a sequential factorization method for recovering the three-dimensional shape of an object and the motion of the camera from a sequence of images, using tracked features. The...

A paraperspective factorization method for shape and motion recovery (1997)

Conrad J. Poelman, Takeo Kanade

Abstract—The factorization method, first developed by Tomasi and Kanade, recovers both the shape of an object and its motion from a sequence of images, using many images and tracking many feature...

Use of Fourier and Karhunen-Loeve decomposition for fast pattern matching with a large set of templates (1997)

Michihiro Uenohara, Takeo Kanade

Abstract—We present a fast pattern matching algorithm with a large set of templates. The algorithm is based on the typical template matching speeded up by the dual decomposition; the Fourier...

Automatically Recognizing Facial Expressions in the Spatio-Temporal Domain (1997)

James J. Lien, Takeo Kanade, Adena J. Zlochower, Ching-Chung Li, Ching-chung Li

We developed a computer vision system that automatically recognizes facial action units (AUs) or AU combinations using Hidden Markov Models (HMMs). AUs are defined as visually discriminable muscle...

Cooperative Multi-Sensor Video Surveillance (1997)

Takeo Kanade, Robert T. Collins, Alan J. Lipton, P. Anandan, Peter Burt, Lambert Wixson

Carnegie Mellon University (CMU) and the David Sarnoff Research Center (Sarnoff) have begun a joint, integrated feasibility demonstration in the area of Video Surveillance and Monitoring (VSAM). The...

Name-It: Naming and Detecting Faces in Video by the Integration of Image and Natural Language Processing (1997)

Shin'ichi Satoh, Takeo Kanade

We have been developing Name-It, a system that associates faces and names in news videos. First, as the only knowledge source, the system is given news videos which include image sequences and...

Spotting by Association in News Video (1997)

Takeo Kanade

This paper introduces the Spotting by Association method for video analysis, which is a novel method to detect video segments with typical semantics. Video data contains various kinds of information...

Volumetric Object Modeling for Surgical Simulation (1997)

Eric Grimson, Ron Kikinis, Hugh Lauer, Neil Mckenzie, Andrew Mor, Shin Nakajima, ...

Surgical simulation has many applications in medical education, surgical training, surgical planning, and intra-operative assistance. However, extending current surface-based computer graphics...

Affine Structure from Line Correspondences with Uncalibrated Affine Cameras (1997)

Long Quan, Takeo Kanade

This paper presents a linear algorithm for recovering 3D affine shape and motion from line correspondences with uncalibrated affine cameras. The algorithm requires a minimum of seven line...

Geometric Constraint Analysis and Synthesis: Methods for Improving Shape-Based Registration Accuracy (1997)

David A. Simon, Takeo Kanade

. Shape-based registration is a process for estimating the transformation between two shape representations of an object. It is used in many image-guided surgical systems to establish a...

Simulating Arthroscopic Knee Surgery using Volumetric Object Representations, Real-Time Volume Rendering and Haptic Feedback (1997)

Sarah Gibson, Joe Samosky, Andrew Mor, Christina Fyock, Eric Grimson, Takeo Kanade, ...

A system for simulating arthroscopic knee surgery that is based on volumetric object models derived from 3D Magnetic Resonance Imaging is presented. Feedback is provided to the user via real-time...

Accessing Video Contents: Cooperative Approach . . . (1997)

Takeo Kanade

Digital video libraries become much more important. In achieving them, access and extraction methods of semantic contents of videos are essential technologies. The paper demonstrates the benefits of...

Affine Structure from Line Correspondences with Uncalibrated Affine Cameras (1997)

Long Quan, Takeo Kanade

This paper presents a linear algorithm for recovering 3D affine shape and motion from line correspondences with uncalibrated affine cameras. The algorithm requires a minimum of seven line...

A Tracker for Broken and Closely-Spaced Lines (1997)

Naoki Chiba, Takeo Kanade

We propose an automatic line tracking method which can deal with broken or closely-spaced line segments more accurately than previous methods over an image sequence. The method uses both grey scale...

School of Computer Science (1997)

Toshihiko Morita, Takeo Kanade

We present a sequential factorization method for recovering the three-dimensional shape of an object and the motion of the camera from a sequence of images, using tracked features. The factorization...

Automatically recognizing facial expressions in spatio-temporal domain using hidden markov models (1997)

James J. Lien, Takeo Kanade, Adena J. Zlochower, Jeffrey F. Cohn, Ching-chung Li

We developed a computer vision system that automatically recognizes facial action units (AUs) or AU combinations using Hidden Markov Models (HMMs). AUs are defined as visually discriminable muscle...

A sequential factorization method for recovering shape and motion from image streams (1997)

Toshihiko Morita, Takeo Kanade

We present a sequential factorization method for recovering the three-dimensional shape of an object and the motion of the camera from a sequence of images, using tracked features. The factorization...

A paraperspective factorization method for shape and motion recovery (1997)

Conrad J. Poelman, Takeo Kanade

The factorization method, first developed by Tomasi and Kanade, recovers both the shape of an object and its motion from a sequence of images, using many images and tracking many feature points to...

Geometric constraint analysis and synthesis: Methods for improving shapebased registration accuracy (1997)

David A. Simon, Takeo Kanade

Abstract. Shape-based registration is a process for estimating the transformation between two shape representations of an object. It is used in many image-guided surgical systems to establish a...

Simulating arthroscopic knee surgery using volumetric object representations, real-time volume rendering and haptic feedback (1997)

Sarah Gibson, Joe Samosky, Andrew Mor, Christina Fyock, Eric Grimson, Takeo Kanade, ...

A system for simulating arthroscopic knee surgery that is based on volumetric object models derived from 3D Magnetic Resonance Imaging is presented. Feedback is provided to the user via real-time...

Simulating arthroscopic knee surgery using volumetric object representations, real-time volume rendering and haptic feedback (1997)

Sarah Gibson, Joseph Samosky, Andrew Mor, Christina Fyock, Eric Grimson, Takeo Kanade, ...

A system for simulating arthroscopic knee surgery that is based on volumetric object models derived from 3D Magnetic Resonance Imaging is presented. Feedback is provided to the user via real-time...

Video Skimming and Characterization through the Combination of Image and Language Understanding Techniques (1997)

Michael A. Smith, Takeo Kanade

Digital video is rapidly becoming important for educa-tion, entertainment, and a host of multimedia applications. With the size of the video collections growing to thousands of hours, technology is...

Simulating arthroscopic knee surgery using volumetric object representations, real-time volume rendering and haptic feedback (1997)

Sarah Gibson, Joe Samosky, Andrew Mor, Christina Fyock, Takeo Kanade, Ron Kikinis, ...

A system for simulating arthroscopic knee surgery that is based on volumetric object models derived from 3D Magnetic Resonance Imaging is presented. Feedback is provided to the user via real-time...

What You can See Is What You can Feel" - Development of a Visual/Haptic Interface to Virtual Environments (1996)

Yasuyoshi Yokokohji, Ralph L. Hollis, Takeo Kanade

In this paper, we propose a new concept of visual/haptic interfaces called WYSIWYF display. The proposed concept provides correct visual/haptic registration using a visionbased object tracking...

Neural Network-Based Face Detection (1996)

Henry Rowley, Shumeet Baluja, Takeo Kanade

We present a neural network-based face detection system. A retinally connected neural network examines small windows of an image, and decides whether each window contains a face. The system...

A Stereo Machine for Video-rate Dense Depth Mapping and Its New Applications (1996)

Takeo Kanade, Atsushi Yoshida, Kazuo Oda, Hiroshi Kano, Masaya Tanaka

this paper we will present two examples, z keying and virtualized reality, on which we are currently working.

"What You can See Is What You can Feel." - Development of a Visual/Haptic Interface to Virtual Environment (1996)

Yasuyoshi Yokokohji, Ralph L. Hollis, Takeo Kanade

In this paper, we propose a new concept of visual/haptic interfaces called WYSIWYF display. The proposed concept provides correct visual/haptic registration using a visionbased object tracking...

A Sorting Image Sensor: An Example of Massively Parallel Intensity-to-Time Processing for Low-Latency Computational Sensors (1996)

Vladimir Brajovic, Takeo Kanade

The need for low-latency vision systems is growing: high speed visual servoing and vision--based human computer interface. In this paper we present a new intensity--to--time processing paradigm...

Neural Network-Based Face Detection (1996)

Henry A. Rowley, Shumeet Baluja, Takeo Kanade

We present a neural network-based face detection system. A retinally connected neural network examines small windows of an image, and decides whether each window contains a face. The system...

Neural Network-Based Face Detection (1996)

Henry A. Rowley, Shumeet Baluja, Takeo Kanade

We present a neural network-based upright frontal face detection system. A retinally connected neural network examines small windows of an image, and decides whether each window contains a face. The...

A Sorting Computational Sensor (1996)

V. Brajovic, Takeo Kanade

The need for low-latency vision systems is growing: high speed visual servoing and vision--based human computer interface. In this paper we present a new intensity--to--time processing paradigm...

Name-It: Association of Face and Name in Video (1996)

Shin'ichi Satoh, Takeo Kanade, The Presidental Race

This paper proposes a novel approach to extract meaningful content information from video by collaborative integration of image understanding and natural language processing. As an actual example, we...

Simulation, Planning, and Execution of Computer-Assisted Surgery (1996)

Takeo Kanade Pi, Takeo Kanade, Pi Anthony, M. Digioia, ...

the critical postoperative stress state and load transfer mechanism, a surgical simulator must model the actual implantation of a component into the prepared cavity within the patient's bone....

Techniques for the Creation and Exploration of Digital Video Libraries (1996)

Michael Christel, Scott Stevens, Takeo Kanade, Michael Mauldin, Raj Reddy, Howard Wactlar

Introduction The Information Age is fully upon us. A recent article noted that there are perhaps 50 million people using the Internet on a regular basis, and that "the current growth rate is...

A Factorization Method for Affine Structure from Line Correspondences (1996)

Long Quan, Takeo Kanade

A family of structure from motion algorithms called the factorization method has been recently developed from the orthographic projection model to the affine camera model [23, 16, 18]. All these...

A Sequential Factorization Method For Recovering Shape And Motion From Image Streams (1996)

Toshihiko Morita, Takeo Kanade

We present a sequential factorization method for recovering the three-dimensional shape of an object and the motion of the camera from a sequence of images, using tracked features. The factorization...

What You See Is What You Can Feel-Development of a Visual/Haptic Interface to Virtual Environment (1996)

Yasuyoshi Yokokohji, Ralph L. Hollis, Takeo Kanade

In this paper, we propose a new concept of visual/haptic interfaces called WYSIWYF display. The proposed concept provides correct visual/haptic registration using a visionbased object tracking...

Simulation, planning, and execution of computer-assisted surgery (1996)

Takeo Kanade, Pi Anthony, M. Digioia, Mike Blackwell, ...

element methods, computer-assisted surgery, image-guided surgery,intra-surgical navigational guidance, medical robotics, surface-based registration, surgical simulation. T HIS I. Project Summary...

A stereo machine for video-rate dense depth mapping and its new applications (1996)

Takeo Kanade, Atsushi Yoshida, Kazuo Oda, Hiroshi Kano, Masaya Tanaka

We have developed a video-rate stereo machine that has the capability of generating a dense depth map at the video rate. The performance bench marks of the CMU video-rate stereo machine are: 1) multi...

Intelligent Access (1996)

To Digital Video, Howard D. Wactlar, Takeo Kanade, Michael A. Smith, Scott M. Stevens

e start with a highly accurate, speaker-independent, connected speech recognizer that automatically transcribes video soundtracks. A language-understanding system then analyzes and organizes the...

Synchronous Capture of Image Sequences from Multiple Cameras (1995)

Narayanan Peter, Peter R, Takeo Kanade

Several applications today need to digitally capture every frame of a video stream or a camera. These range from psychological studies to surveillance to video processing. Some applications also need...

Human Face Detection in Visual Scenes (1995)

Henry A. Rowley, Shumeet Baluja, Takeo Kanade

We present a neural network-based face detection system. A retinally connected neural network examines small windows of an image, and decides whether each window contains a face. The system...

A Multi-body Factorization Method for Motion Analysis (1995)

João Costeira, Takeo Kanade

The structure-from-motion problem has been extensively studied in the field of computer vision. Yet, the bulk of the existing work assumes that the scene contains only a single moving object. The...

Video skimming for quick browsing based on audio and image characterization (1995)

Michael A. Smith, Takeo Kanade

Digital video is rapidly becoming an important source for information, entertainment and a host of multimedia applications. With the size of these collections growing to thousands of hours,...

Video-Rate Z Keying: A New Method for Merging Images (1995)

Takeo Kanade, Kazuo Oda, Atsushi Yoshida, Masaya Tanaka, Hiroishi Kano

Video-rate z keying is a new image keying method for merging real and synthetic images in real time. In visual media communication and display, it is often necessary to merge video signals from a...

Visual Tracking of Self-Occluding Articulated Objects (1995)

James M. Rehg, Takeo Kanade

Computer sensing of hand and limb motion is an important problem for applications in human-computer interaction, virtual reality, and athletic performance measurement. We describe a framework for...

Video Skimming for Quick Browsing based on Audio and Image Characterization (1995)

Michael A. Smith, Takeo Kanade

Digital video is rapidly becoming an important source for information, entertainment and a host of multimedia applications. With the size of these collections growing to thousands of hours,...

A Multi-body Factorization Method for Motion Analysis (1995)

Joao Costeira Takeo, Takeo Kanade

The structure-from-motion problem has been extensively studied in the field of computer vision. Yet, the bulk of the existing work assumes that the scene contains only a single moving object. The...

Vision-Based Object Registration for Real-Time Image Overlay (1995)

Michihiro Uenohara, Takeo Kanade, T. Kanade

This paper presents a computer vision based technique for object registration, real-time tracking, and image overlay. The capability can be used to superimpose registered medical images such as those...

A Multi-body Factorization Method for Motion Analysis (1995)

João Costeira, Takeo Kanade

The structure-from-motion problem has been extensively studied in the field of computer vision. Yet, the bulk of the existing work assumes that the scene contains only a single moving object. The...

Vision-Based Object Registration for Real-Time Image Overlay (1995)

Michihiro Uenohara, Takeo Kanade

This paper presents computer vision based techniques for object registration, real-time tracking, and image overlay. The capability can be used to superimpose registered images such as those from CT...

Human Face Detection in Visual Scenes (1995)

Henry Rowley, Shumeet Baluja, Takeo Kanade

We present a neural network-based face detection system. A retinally connected neural network examines small windows of an image, and decides whether each window contains a face. The system...

A Multi-body Factorization Method (1995)

For Motion Analysis, João Costeira, Takeo Kanade

The structure-from-motion problem has been extensively studied in the field of computer vision. Yet, the bulk of the existing work assumes that the scene contains only a single moving object. The...

Human face detection in visual scenes (1995)

Henry A. Rowley, Shumeet Baluja, Takeo Kanade

We present a neural network-based face detection system. A retinally connected neural network examines small windows of an image, and decides whether each window contains a face. The system...

Model-based tracking of self-occluding articulated objects (1995)

James M. Rehg, Takeo Kanade

Computer sensing of hand and limb motion is an important problem for applications in humancomputer interaction and computer graphics. We describe aframework for local tracking of self-occluding...

Techniques for fast and accurate intra-surgical registration (1995)

David A. Simon, Martial Hebert, Takeo Kanade

The goal of intra-surgical registration is to establish a common reference frame between pre-surgical and intra-surgical 3-D data sets that correspond to the same anatomy. This paper presents two...

CMU-CS-95-158R (1995)

Henry A. Rowley, Shumeet Baluja, Takeo Kanade

We present a neural network-based face detection system. A retinally connected neural network examines small windows of an image, and decides whether each window contains a face. The system...

Model-Based Tracking of Self-Occluding Articulated Objects (1995)

James Rehg, Takeo Kanade

Computer sensing of hand and limb motion is an important problem for applications in humancomputer interaction and computer graphics. We describe a framework for local tracking of self-occluding...

A Multibaseline Stereo System with Active Illumination and Real-time Image Acquisition (1995)

Sing Bing, Jon A. Webb, C. Lawrence Zitnick, Takeo Kanade

We describe our implementation of a parallel depth recovery scheme for a four-camera multibaseline stereo in a convergent configuration. Our system is capable of image capture at video rate. This is...

Virtualized Reality: Concepts and Early Results (1995)

Takeo Kanade

The visual medium evolved from early paintings to the realistic paintings of the classical era to photographs. The medium of moving imagery started with motion pictures. Television and video...

A multi-body factorization method for motion analysis (1995)

João Costeira, Takeo Kanade

The structure-from-motion problem has been extensively studied in the field of computer vision. Yet, the bulk of the existing work assumes that the scene contains only a single moving object. The...

Techniques for fast and accurate intra-surgical registration (1995)

David A. Simon, Martial Hebert, Takeo Kanade

The goal of intra-surgical registration is to establish a common reference frame between pre-surgical and intra-surgical 3-D data sets that correspond to the same anatomy. This paper presents two...

Synchronous Capture of Image Sequences from Multiple Cameras (1995)

P. J. Narayanan, Peter R, Takeo Kanade

Several applications today need to digitally capture every frame of a video stream or a camera. These range from psychological studies to surveillance to video processing. Some applications also need...

Masaya Tanaka, Hiroshi Kano (1995)

Takeo Kanade, Kazuo Oda, Atsushi Yoshida

contained in this document are those of the author and should not be interpreted as necessarily representing official policies or endorsements, either expressed or implied, of the Department of the...

Parameterization and Adaptive Control of Space Robot Systems (1995)

Xu, Yangsheng, Shum, Heung-Yeung, Kanade, Takeo, Lee, Ju-Jang

In space application, robot system are subject to unknown or unmodeled dynamics, for example, in the tasks of transporting an unknown payload or catching an unmodeled moving object. We discuss the...

Visual tracking of high DOF articulated structures: An application to human hand tracking (1994)

James M. Rehg, Takeo Kanade

Abstract. Passive sensing of human hand and limb motion is important for a wide range of applications from human-computer interaction to athletic performance measurement. High degree of freedom...

A Sequential Factorization Method for Recovering Shape and Motion from Image Streams (1994)

Toshihiko Morita, Takeo Kanade

We present a sequential factorization method for recovering the three-dimensional shape of an object and the motion of the camera from a sequence of images, using tracked features. The factorization...

Virtual Space Teleconferencing using a Sea of Cameras (1994)

Henry Fuchs, Gary Bishop, Kevin Arthur, Leonard McMillan, Ruzena Bajcsy, ...

A new approach to telepresence is presented in which a multitude of stationary cameras are used to acquire both photometric and depth information. A virtual environment is constructed by displaying...

An Active Multibaseline Stereo System With Real-Time Image Acquisition (1994)

Sing Bing Kang, Jon Webb, C. Lawrence Zitnick, Takeo Kanade

We describe our four-camera multibaseline stereo system in a convergent configuration and our implementation of a parallel depth recovery scheme for this system. Our system is capable of image...

Sensor Placement Design for Object Pose Determination with Three Light-Stripe Range Finders (1994)

Keiichi Kemmotsu, Takeo Kanade

The pose of a polyhedral object can be determined with range data obtained from a set of simple light-stripe range sensors. However, localization results are highly dependent on sensor placement....

Sensor Placement Design for Object Pose Determination with Three Light-Stripe Range Finders (1994)

Keiichi Kemmotsu Takeo, Takeo Kanade

The pose of a polyhedral object can be determined with range data obtained from a set of simple light-stripe range sensors. However, localization results are highly dependent on sensor placement....

DigitEyes: Vision-Based Hand Tracking for Human-Computer Interaction (1994)

James Rehg, Takeo Kanade

Computer sensing of hand and limb motion is an important problem for applications in HumanComputer Interaction (HCI), virtual reality, and athletic performance measurement. Commercially available...

Visual tracking of high DOF articulated structures: An application to human hand tracking (1994)

James M. Rehg, Takeo Kanade

Abstract. Passive sensing of human hand and limb motion is important for a wide range of applications from human-computer interaction to athletic performance measurement. High degree of freedom...

Visual tracking of self-occluding articulated objects (1994)

James M. Rehg, Takeo Kanade

50559. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the o cial policies, either expressed or implied, of NASA or the...

Sensor placement design for object pose determination with three light-stripe range finders (1994)

Keiichi Kemmotsu, Takeo Kanade

interpreted as representing the o cial policies, either expressed or implied, of the U.S. government.

Digiteyes: Vision-based hand tracking for human-computer interaction (1994)

James M. Rehg, Takeo Kanade

Computer sensing of hand and limb motion is an important problem for applications in Human-Computer Interaction (HCI), virtual reality, and athletic performance measurement. Commercially available...

Real-time 3-D pose estimation using a high-speed range sensor (1994)

David A. Simon, Martial Hebert, Takeo Kanade

This paper describes a system which can perform full 3-D pose estimation of a single arbitrarily shaped, rigid object at rates up to 10Hz. A triangular mesh model of the object to be tracked is...

Creating benchmarking problems in machine vision: scientific challenge problems (1993)

Oscar Firschein, Martin A. Fischler, Takeo Kanade

We discuss the need for a new series of benchmarks in the vision field. to provide a direct quantitative measure of progress understandable to sponsors of research as well as a guide to practitioners...

A Paraperspective Factorization Method for Shape and. . . (1993)

Conrad J. Poelman, Takeo Kanade

The factorization method, first developed by Tomasi and Kanade, recovers both the shape of an object and its motion from a sequence of images, using many images and tracking many feature points to...

DigitEyes: Vision-Based Human Hand Tracking (1993)

James M. Rehg, Takeo Kanade

Passive sensing of human hand and limb motion is important for a wide range of applications from human-computer interaction to athletic performance measurement. High degree of freedom articulated...

CMU Very Fast Range-Imaging System (1993)

Shigeyuki Tada, Andrew Gruss, Takeo Kanade

We present a high-speed range-imaging system based on a VLSI computational sensor developed in the CMU Computer Science Department. The VLSI range sensor is a custom chip consisting of an array of...

CMU very fast range-imaging system (1993)

Shigeyuki Tada, Andrew Gruss, Takeo Kanade

We present a high-speed range-imaging system based on a VLSI computational sensor developed in the CMU Computer Science Department. The VLSI range sensor is a custom chip consisting of an array of...

DigitEyes: vision-based human hand tracking (1993)

James M. Rehg, Takeo Kanade

50559. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the o cial policies, either expressed or implied, of NASA or the...

Shape and Motion from Image Streams: a Factorization Method: Full Report on the Orthographic Case (1992)

Tomasi, Carlo, Kanade, Takeo

Inferring scene geometry and camera motion from a stream of images is possible in principle, but is an ill-conditioned problem when the objects are distant with respect to their size. We have...

Shape and Motion from Image Streams: a Factorization Method: Full Report on the Orthographic Case (1992)

Tomasi, Carlo, Kanade, Takeo

Inferring scene geometry and camera motion from a stream of images is possible in principle, but is an ill-conditioned problem when the objects are distant with respect to their size. We have...

Shape and Motion from Image Streams: a Factorization Method - Full Report on the Orthographic Case (1992)

Carlo Tomasi, Takeo Kanade

Inferring scene geometry and camera motion from a stream of images is possible in principle, but is an ill-conditioned problem when the objects are distant with respect to their size. We have...

A Paraperspective Factorization Method for Shape and Motion Recovery (1992)

Conrad Poelman, Takeo Kanade

In this paper, we present a method for recovering both the shape of an object and its motion relative to the camera from a sequence of images of the object, using feature points tracked throughout...

A Papaperspective Factorization Method for Shape and Motion Recovery (1992)

Conrad Poelman, Takeo Kanade

In this paper, we present a method for recovering both the shape of an object and its motion relative to the camera from a sequence of images of the object, using feature points tracked throughout...

Integrated Sensor and Range-Finding Analog Signal Processor (1991)

Andrew Gruss, L. Richard Carley, Takeo Kanade, Senior Member

Abstract--In this paper we present an IC array of photosensor and analog signal processor cells that acquires 1000 frames of light-stripe range data per second--two orders of magnitude faster than...

shape and motion from image streams: a factorization method (1991)

Carlo Tomasi, Takeo Kanade

The factorization method described in this series of reports requires an algorithm to track the motion of features in an image stream. Given the small inter-frame displacement made possible by the...

Integrated sensor and range finding analog signal processor (1991)

L. Richard Carley, Andrew Gross, Takeo Kanade

Rangefinding, the measurement of the three dimensional profile of an object or scene, is a critical component for many robotic and sensing applications. This paper describes a light-stripe...

Shape and Motion from Image Streams: a Factorization Method (1991)

Carlo Tomasi, Takeo Kanade

Inferring scene geometry and camera motion from a stream of images is possible in principle, but is an ill-conditioned problem when the objects are distant with respect to their size. We have...

Detection and Tracking of Point Features (1991)

Carlo Tomasi, Takeo Kanade

The factorization method described in this series of reports requires an algorithm to track the motion of features in an image stream. Given the small inter-frame displacement made possible by the...

Shape and Motion from Image Streams: a Factorization Method 2. Point Features in 3D Motion (1991)

Carlo Tomasi, Takeo Kanade

In principle, three orthographic images of four points are sufficient to recover the positions of the points relative to each other (shape), and the viewpoints from which the images were taken...

Detection and Tracking of Point Features (1991)

Carlo Tomasi Takeo, Takeo Kanade

The factorization method described in this series of reports requires an algorithm to track the motion of features in an image stream. Given the small inter-frame displacement made possible by the...

. Point Features in 3D Motion (1991)

Carlo Tomasi Takeo, Takeo Kanade

In principle, three orthographic images of four points are sufficient to recover the positions of the points relative to each other (shape), and the viewpoints from which the images were taken...

shape and motion from image streams: a factorization method (1991)

Carlo Tomasi, Takeo Kanade

The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the o cial policies, either expressed or implied, of the U.S. government.

T.Kanade,"Shape and Motion from Image Streams: AFactorization Method-2. PointFeatures in 3D Motion (1991)

Carlo Tomasi, Takeo Kanade

The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the o cial policies, either expressed or implied, of the U.S. government.

T.Kanade,"Shape and Motion from Image Streams: AFactorization Method-2. PointFeatures in 3D Motion (1991)

Carlo Tomasi, Takeo Kanade

The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the o cial policies, either expressed or implied, of the U.S. government.

A Physical Approach to Color Image Understanding (1990)

Gudrun J. Klinker, Steven A. Shafer, Takeo Kanade

In this paper, we present an approach to color image understanding that can be used to segment and analyze surfaces with color variations due to highlights and shading. The work is based on a theory...

Contents (1990)

Shree K. Nayar, Katsushi Ikeuchi, Takeo Kanade

0 1990 Camegie Mellon University This research was supported in pan by Westinghouse Elecaic Corporation and in pan by DARPA under contract F33615-87-C-1499. She K. Nayar was supported by Wesunghouse

Contents (1990)

William Whittaker, Takeo Kanade, Tom Mitchell

contained in this document are those of the authors and should not be interpreted as representing

Principal Investigators (1989)

Takeo Kanade, Tom Mitchell, William Whittaker

@ 1989 Carnegie Mellon University..--.-,I,--This research was sponsored by NASA under Contract NAGW-1175. The views and con-clusions contained in this document arc those of the authors and should not...

Computer Analysis of Regular Repetitive Textures (1989)

Takeo Kanade

Regular rcpifive t. cxmrcs arc common in real-world sccn occurring in Seth ramhal and man.made environments. Their analysis is important for image smcmafio. and f = shape racevery fzo mrf,, texture....

Image segmentation and reflection analysis through color (1988)

Gudrun J. Klinker, Steven A. Shafer, Takeo Kanade

In this paper, we present an approach to color im-age understanding that can be used to segment and analyze surfaces with color variations due to high-lights and shading. We begin with a theory that...

Model-based vision by cooperative processing of evidence and hypotheses using configuration spaces (1988)

Yoshinori Kuno, Katsushi Ikeuchi, Takeo Kanade

Model-based vision by cooperative processing of evidence and hypotheses using configuration spaces

The measurement of highlights in color images (1988)

Gudrun J. Klinker, Steven A. Shafer, Takeo Kanade

In this paper, we present an approach to color image understanding that accounts for color variations due to highlights and shading. We demonstrate that the reflected light from every point on a...

Color Image Analysis (1988)

With An Intrinsic, Gudrun J. Klinker, Steven A. Shafer, Takeo Kanade

In this paper, we present an approach to color image understanding that can be used to segment and analyze surfaces with color variations due to highlights and shading. We begin with a theory - the...

3-d vision techniques for autonomous vehicles (1988)

Martial Hebert, Takeo Kanade, Inso Kweon

those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the funding agencies. 4 Contents

Using a Color Reflection Model to Separate Highlights from Object Color (1987)

Gudrun J. Klinker, Steven A. Shafer, Takeo Kanade

Current methods for image segmentation are confused by artifacts such as highlights, because they are not based on any physical model of these phenomena. In this paper, we present an approach to...

Overview Chronology Personnel Publications (1987)

Charles Thorpe, Takeo Kanade

Topographic Laboratories under contract DACA76-85-C-0003. I

Modeling sensor performance for model-based vision (1987)

Katsushi Ikeuchi, Takeo Kanade

The model-based vision requires object appearances in the computer. How 8n object appears in the image is a result of interaction between the object properties and the sensor characteristics. Thus,...

First results in robot road-following (1985)

Richard Wallace, Anthony Stentz, Charles Thorpe, Hans Moravec, William Whittaker, Takeo Kanade

The new Carnegie Mellon Autonomous I and Vehicle group has produced the first demonstrations of road following robots. In this paper we first describe the robots that are part of the CMU Autonomous...

Mapping image properties into shape constraints: skewed symmetry, affine-transformable patterns, and the shape-from-texture paradigm (1983)

Takeo Kanade, John R. Kender

In this paper we demonstrate two new approaches to deriving three-dimensional surface orientation information (“shape”) from two-dimensional image cues. The two approaches are the method of...

Using Shadows in Finding Surface Orientations, (1982)

Shafer,Steven A., Kanade,Takeo

Given a line drawing from an image with shadow regions identified, the shapes of the shadows can be used to generate constraints on the orientations of the surfaces involved. This paper describes the...

Control of a direct-drive arm (1982)

Haruhiko Asada, Takeo Kanade, Ichiro Takeyama

12 direct-drivc arm is a new mechanical ami in which the shafts of articulatcd joints arc directly co~iplcd to thc rotors of high pcrformance torque motors. Since the arm does not contain any gcars...

An Iterative Image Registration Technique with an Application to Stereo Vision (1981)

Bruce D. Lucas, Takeo Kanade

Image registration finds a variety of applications in computer vision. Unfortunately, traditional image registration techniques tend to be costly. We present a new image registration technique that...

Location of source file: /usnO/pkk/project/reports/kin~~ (1956)

Pradeep K. Khosla, Takeo Kanade

Pittsburgh. Pa. 15213. Some of thc idcas expresscd in this documcnt may be only partially developed or erroncous. Distribution of this document outside the immcdiatc working community is discouraged;...