Search For:

Displaying 1-33 out of 33 total
Geodesic Mapping for Dynamic Surface Alignment
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Tony Tung,Takashi Matsuyama
Issue Date:May 2014
pp. 1-1
This paper presents a novel approach that achieves dynamic surface alignment by geodesing mapping. The surfaces are 3D manifold meshes representing non-rigid objects in motion (e.g., humans) which can be obtained by multiview stereo reconstruction. The pro...
 
A Pixel-Wise Varifocal Camera Model for Efficient Forward Projection and Linear Extrinsic Calibration of Underwater Cameras with Flat Housings
Found in: 2013 IEEE International Conference on Computer Vision Workshops (ICCVW)
By Ryo Kawahara,Shohei Nobuhara,Takashi Matsuyama
Issue Date:December 2013
pp. 819-824
This paper is aimed at presenting a new virtual camera model which can efficiently model refraction through flat housings in underwater photography. The key idea is to employ a pixel-wise virtual focal length concept to encode the refractive projection ins...
 
Gaze Probing: Event-Based Estimation of Objects Being Focused On
Found in: Pattern Recognition, International Conference on
By Ryo Yonetani, Hiroaki Kawashima, Takatsugu Hirayama, Takashi Matsuyama
Issue Date:August 2010
pp. 101-104
We propose a novel method to estimate the object that a user is focusing on by using the synchronization between the movements of objects and a user's eyes as a cue. We first design an event as a characteristic motion pattern, and we then embed it within t...
 
Dynamic surface matching by geodesic mapping for 3D animation transfer
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Tony Tung, Takashi Matsuyama
Issue Date:June 2010
pp. 1402-1409
This paper presents a novel approach that achieves complete matching of 3D dynamic surfaces. Surfaces are captured from multi-view video data and represented by sequences of 3D manifold meshes in motion (3D videos). We propose to perform dense surface matc...
 
Speaker detection using the timing structure of lip motion and sound
Found in: Computer Vision and Pattern Recognition Workshop
By Yu Horii, Hiroaki Kawashima, Takashi Matsuyama
Issue Date:June 2008
pp. 1-8
In this paper, we propose a novel approach to speaker detection by an integration of audio-visual information using the cue of timing structure. We first extract feature sequences of lip motion and sound, and segment each of them into temporal intervals. T...
 
Simultaneous super-resolution and 3D video using graph-cuts
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Tony Tung, Shohei Nobuhara, Takashi Matsuyama
Issue Date:June 2008
pp. 1-8
This paper presents a new method to increase the quality of 3D video, a new media developed to represent 3D objects in motion. This representation is obtained from multi-view reconstruction techniques that require images recorded simultaneously by several ...
 
Interval-Based Linear Hybrid Dynamical System for Modeling Cross-Media Timing Structures in Multimedia Signals
Found in: Image Analysis and Processing, International Conference on
By Hiroaki Kawashima, Takashi Matsuyama
Issue Date:September 2007
pp. 789-794
In this paper, we propose a computational scheme named an interval-based linear hybrid dynamical system (ILHDS) to represent complex dynamic events based on temporal intervals, each of which is characterized by linear dynamics and its duration. We then pro...
 
Topology matching for 3D video compression
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Tony Tung, Francis Schmitt, Takashi Matsuyama
Issue Date:June 2007
pp. 1-8
This paper presents a new technique to reduce the storage cost of high quality 3D video. In 3D video [12], a sequence of 3D objects represents scenes in motion. Every frame is composed by one or several accurate 3D meshes with attached high fidelity proper...
 
Modeling Dynamic Structure of Human Verbal and Nonverbal Communication
Found in: Informatics Research for Development of Knowledge Society Infrastructure, International Conference on
By Takashi Matsuyama, Hiroaki Kawashima
Issue Date:January 2007
pp. 3-10
In human communication, dynamics of communication, i.e. timing structure of utterances, nodding, gesture, pause and so on, plays a crucial role to realize smooth natural communication. We proposed a computational scheme named Interval-based Linear Hybrid D...
 
Parallel Pipeline Volume Intersection for Real-Time 3D Shape Reconstruction on a PC Cluster
Found in: Computer Vision Systems, International Conference on
By Xiaojun Wu, Osamu Takizawa, Takashi Matsuyama
Issue Date:January 2006
pp. 4
The human activity monitoring is one of the major tasks in the field of computer vision. Recently, not only the 2D images but also 3D shapes of a moving person are desired in kinds of cases, such as motion analysis, security monitoring, 3D video creation a...
 
Heterogeneous Deformation Model for 3D Shape and Motion Recovery from Multi-Viewpoint Images
Found in: 3D Data Processing Visualization and Transmission, International Symposium on
By Shohei Nobuhara, Takashi Matsuyama
Issue Date:September 2004
pp. 566-573
This paper presents a framework for dynamic 3D shape and motion reconstruction from multi-viewpoint images using a deformable mesh model. By deforming a mesh at a frame to that at the next frame, we can obtain both 3D shape and motion of the object simulta...
 
Difference Sphere: An Approach to Near Light Source Estimation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Takeshi Takai, Koichiro Niinuma, Atsuto Maki, Takashi Matsuyama
Issue Date:July 2004
pp. 98-105
We present a novel approach for estimating lighting sources from a single image of a scene that is illuminated by near point light sources, directional light sources and ambient light. We propose to employ a pair of reference spheres as light probes and in...
 
Active Wearable Vision Sensor: Recognition of Human Activities and Environments
Found in: Informatics Research for Development of Knowledge Society Infrastructure, International Conference on
By Kazuhiko Sumi, Akihiro Sugimoto, Takashi Matsuyama, Masato Toda, Sotaro Tsukizawa
Issue Date:March 2004
pp. 15-22
To realize a symbiotic relationship between humans and computers, it is crucial to estimate the external and internal state of the human by observation. One promising approach is to acquire the same visual information as the human acquires. In this paper, ...
 
Exploitation of 3D Video Technologies
Found in: Informatics Research for Development of Knowledge Society Infrastructure, International Conference on
By Takashi Matsuyama
Issue Date:March 2004
pp. 7-14
3D video is NOT an artificial CG animation but a real 3D movie recording the full 3D shape, motion, and precise surface color & texture of real world objects. It enables us to observe real object behaviors from any viewpoints as well as to see pop-up 3...
 
Real-Time Cooperative Multi-Target Tracking by Communicating Active Vision Agents
Found in: Pattern Recognition, International Conference on
By Norimichi Ukita, Takashi Matsuyama
Issue Date:August 2002
pp. 20014
We present a real-time cooperative multi-target tracking system. The system consists of a group of Active Vision Agents (AVAs), where an AVA is a logical model of a network-connected computer with an active camera. All AVAs cooperatively track their target...
 
Detecting a Gazing Region by Visual Direction and Stereo Cameras
Found in: Pattern Recognition, International Conference on
By Akihiro Sugimoto, Akihiro Nakayama, Takashi Matsuyama
Issue Date:August 2002
pp. 30278
We develop a wearable vision system that consists of a user's visual direction sensor and stereo cameras. First, we establish a method for calibrating the system so that it can detect user's blink points even in a real situation such that the depth of blin...
 
Generation, Visualization, and Editing of 3D Video
Found in: 3D Data Processing Visualization and Transmission, International Symposium on
By Takashi Matsuyama, Takeshi Takai
Issue Date:June 2002
pp. 234
3D video is the ultimate image medium recording dynamic visual events in the real world as is. Recorded object behaviors can be observed from any viewpoint, because 3D video records the object?s full 3D shape, motion, and precise surface properties (i.e. c...
 
Multilinear Relationships between the Coordinates of Corresponding Image Conics
Found in: Pattern Recognition, International Conference on
By Akihiro Sugimoto, Takashi Matsuyama
Issue Date:September 2000
pp. 1550
This paper presents a study, based on conic correspondences, on the relationship between multiple images acquired by uncalibrated cameras. Representing image conics as points in the five-dimensional projective space allows us to handle image conics in the ...
 
Multiobject Behavior Recognition by Event Driven Selective Attention Method
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Toshikazu Wada, Takashi Matsuyama
Issue Date:August 2000
pp. 873-887
<p><b>Abstract</b>—Recognizing multiple object behaviors from nonsegmented image sequences is a difficult problem because most of the motion recognition methods proposed so far share the limitation of the <it>single-object assumptio...
 
Human Head Tracking Using Adaptive Appearance Models with a Fixed-Viewpoint Pan-Tilt-Zoom Camera
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Kiyotake Yachi, Toshikazu Wada, Takashi Matsuyama
Issue Date:March 2000
pp. 150
We propose a method for detecting and tracking a human head in real time from image sequence. The proposed method has three advantages. 1) We employ a fixed-viewpoint pan-tilt-zoom camera to acquire image sequence. With the camera, we eliminate the variati...
 
Robust Color Segmentation Using the Dichromatic Reflection Model
Found in: Pattern Recognition, International Conference on
By Chun-Kiat Ong, Takashi Matsuyama
Issue Date:August 1998
pp. 780
No summary available.
 
Seeing Behind the Scene: Analysis of Photometric Properties of Occluding Edges by the Reversed Projection Blurring Model
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Naoki Asada, Hisanaga Fujiwara, Takashi Matsuyama
Issue Date:February 1998
pp. 155-167
<p><b>Abstract</b>—This paper analyzes photometric properties of occluding edges and proves that an object surface behind a nearer object is partially observable beyond the occluding edges. We first discuss a limitation of the image blurr...
 
Intrinsic Characterization of Dynamic Surfaces
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Tony Tung,Takashi Matsuyama
Issue Date:June 2013
pp. 233-240
This paper presents a novel approach to characterize deformable surface using intrinsic property dynamics. 3D dynamic surfaces representing humans in motion can be obtained using multiple view stereo reconstruction methods or depth cameras. Nowadays these ...
 
Inter-Reflection Compensation for Immersive Projection Display
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Hitoshi Habe, Nobuo Saeki, Takashi Matsuyama
Issue Date:June 2007
pp. 1-2
This paper proposes an effective method for compensating inter-reflection in immersive projection displays (IPDs). Because IPDs project images onto a screen, which surrounds a viewer, we have perform out both geometric and photometric corrections. Our meth...
 
Deformable Mesh Model for Complex Multi-Object 3D Motion Estimation from Multi-Viewpoint Video
Found in: 3D Data Processing Visualization and Transmission, International Symposium on
By Shohei Nobuhara, Takashi Matsuyama
Issue Date:June 2006
pp. 264-271
We propose a new algorithm using deformable mesh model for complex 3D motion estimation of multiple objects from multi-viewpoint video. In this paper, we define
 
Integrated Event Recognition from Multiple Sources
Found in: Pattern Recognition, International Conference on
By Hiroaki Kawashima, Takashi Matsuyama
Issue Date:August 2002
pp. 20785
This paper proposes a system architecture for event recognition that integrates information from multiple sources (e.g., gesture and speech recognition from distributed sensors in the real world). The proposed system consists of multiple recognizers named ...
 
Learning aspects of interest from Gaze
Found in: Proceedings of the 6th workshop on Eye gaze in intelligent human machine interaction: gaze in multimodal interaction (GazeIn '13)
By Kei Shimonishi, Ryo Yonetani, Takashi Matsuyama, Erina Ishikawa, Hiroaki Kawashima
Issue Date:December 2013
pp. 41-44
This paper presents a probabilistic framework to model the gaze generative process when a user is browsing a content consisting of multiple regions. The model enables us to learn multiple aspects of interest from gaze data, to represent and estimate user's...
     
Predicting where we look from spatiotemporal gaps
Found in: Proceedings of the 15th ACM on International conference on multimodal interaction (ICMI '13)
By Hiroaki Kawashima, Ryo Yonetani, Takashi Matsuyama
Issue Date:December 2013
pp. 421-428
When we are watching videos, there exist spatiotemporal gaps between where we look and what we focus on, which result from temporally delayed responses and anticipation in eye movements. We focus on the underlying structures of those gaps and propose a nov...
     
Semantic interpretation of eye movements using designed structures of displayed contents
Found in: Proceedings of the 4th Workshop on Eye Gaze in Intelligent Human Machine Interaction (Gaze-In '12)
By Erina Ishikawa, Hiroaki Kawashima, Ryo Yonetani, Takashi Matsuyama, Takatsugu Hirayama
Issue Date:October 2012
pp. 1-3
This paper presents a novel framework to interpret eye movements using semantic relations and spatial layouts of displayed contents, i.e., the designed structure. We represent eye movements in a multi-scale, interval-based manner and associate them with va...
     
Multi-mode saliency dynamics model for analyzing gaze and attention
Found in: Proceedings of the Symposium on Eye Tracking Research and Applications (ETRA '12)
By Hiroaki Kawashima, Takashi Matsuyama, Ryo Yonetani
Issue Date:March 2012
pp. 115-122
We present a method to analyze a relationship between eye movements and saliency dynamics in videos for estimating attentive states of users while they watch the videos. The multi-mode saliency-dynamics model (MMSDM) is introduced to segment spatio-tempora...
     
Minimal 3D video
Found in: ACM SIGGRAPH ASIA 2009 Sketches (SIGGRAPH ASIA '09)
By Takashi Matsuyama, Tony Tung
Issue Date:December 2009
pp. 1-1
We present a new concept that achieves the 3D reconstruction of dynamic scenes from multi-view video cameras (or 3D videos) using a minimal number of cameras, as opposed to the present state of the art approaches which require either several tens of camera...
     
Visual filler: facilitating smooth turn-taking in video conferencing with transmission delay
Found in: CHI '08 extended abstracts on Human factors in computing systems (CHI '08)
By Hiroaki Kawashima, Takashi Matsuyama, Takeshi Nishikawa
Issue Date:April 2008
pp. 49-54
Turn-taking in a smooth conversation is supported by the anticipation of the floor handover timing among participants. However, it becomes difficult to maintain natural turn-taking in video conferencing with transmission delays because the utterances and m...
     
Real-time multi-target tracking by cooperative distributed active vision agents
Found in: Proceedings of the first international joint conference on Autonomous agents and multiagent systems: part 2 (AAMAS '02)
By Norimichi Ukita, Takashi Matsuyama
Issue Date:July 2002
pp. 829-838
This paper presents a real-time cooperative multi-target tracking system. The system consists of a group of Active Vision Agents (AVAs), where an AVA is a logical model of a network-connected computer with an active camera. All AVAs cooperatively track the...
     
 1