Capture and representation of human walking in live video sequences
Authors:
- J.M.F. MouraJMJ.M.F. Moura
- 1 June 1999
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 1 (2) , 144-156
Abstract
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 videoKeywords
This publication has 9 references indexed in Scilit:
- Automatic Recognition of Human Walking in Monocular Image SequencesJournal of Signal Processing Systems, 1998
- Model-based estimation of 3D human motion with occlusion based on active multi-viewpoint selection1996
- 3-D model-based tracking of humans in action: a multi-view approach1996
- Retrieving quality video across heterogeneous networks. Video over wirelessIEEE Wireless Communications, 1996
- Virtual Space Teleconferencing: Real-Time Reproduction of 3D Human ImagesJournal of Visual Communication and Image Representation, 1995
- A Computational Approach to Edge DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1986
- Model-based vision: a program to see a walking personImage and Vision Computing, 1983
- Model-based image analysis of human motion using constraint propagationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1980
- Representation and recognition of the spatial organization of three-dimensional shapesProceedings of the Royal Society of London. B. Biological Sciences, 1978