Capture and Representation of Human Walking in Live Video Sequences

Extracting human representations from video has vast applications. In this paper, we present a knowledge-based framework to capture metarepresentations for real-life video with human walkers. The system models the human body as an articulated object and the human walking as a cyclic activity with highly correlated temporal patterns. We extract for each of the body parts its motion, shape, and texture. Once available, this structural information can be used to manipulate or synthesize the original video sequence, or animate the walker with a different motion in a new synthesized video.

[1]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  José M. F. Moura,et al.  Automatic Recognition of Human Walking in Monocular Image Sequences , 1998, J. VLSI Signal Process..

[3]  Jia-Ching Cheng,et al.  Capture and representation of human walking in live monocular video , 1998 .

[4]  Jean-Jacques E. Slotine,et al.  Robot analysis and control , 1988, Autom..

[5]  Fumio Kishino,et al.  Virtual Space Teleconferencing: Real-Time Reproduction of 3D Human Images , 1995, J. Vis. Commun. Image Represent..

[6]  M. P. Murray.  Gait as a total pattern of movement. , 1967, American journal of physical medicine.

[7]  Radu S. Jasinschi,et al.  Retrieving quality video across heterogeneous networks. Video over wireless , 1996, IEEE Wirel. Commun..

[8]  Ioannis A. Kakadiaris,et al.  Model-based estimation of 3D human motion with occlusion based on active multi-viewpoint selection , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  José M. F. Moura,et al.  Content-based video sequence representation , 1995, Proceedings., International Conference on Image Processing.

[10]  David C. Hogg.  Model-based vision: a program to see a walking person , 1983, Image Vis. Comput..

[11]  Murray Mp,et al.  Gait as a total pattern of movement. , 1967 .

[12]  Robert C. Bolles,et al.  Parametric Correspondence and Chamfer Matching: Two New Techniques for Image Matching , 1977, IJCAI.

[13]  Michael J. Black,et al.  Parameterized Modeling and Recognition of Activities , 1999, Comput. Vis. Image Underst..

[14]  Larry S. Davis,et al.  3-D model-based tracking of humans in action: a multi-view approach , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[15]  José M. F. Moura,et al.  Tracking human walking in dynamic scenes , 1997, Proceedings of International Conference on Image Processing.

[16]  José M. F. Moura,et al.  Model-based recognition of human walking in dynamic scenes , 1997, Proceedings of First Signal Processing Society Workshop on Multimedia Signal Processing.

[17]  D. Marr,et al.  Representation and recognition of the spatial organization of three-dimensional shapes , 1978, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[18]  J. O'Rourke,et al.  Model-based image analysis of human motion using constraint propagation , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.