DMCA
Capture and Representation of Human Walking in Live Video Sequences
Cached
Download Links
- [www.ece.cmu.edu]
- [www.ece.cmu.edu]
- [users.ece.cmu.edu]
- [users.ece.cmu.edu]
- [users.ece.cmu.edu]
- [users.ece.cmu.edu]
- DBLP
Other Repositories/Bibliography
BibTeX
@MISC{_captureand,
author = {},
title = {Capture and Representation of Human Walking in Live Video Sequences},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
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 video. Index Terms—Capture, cyclic motion, human walkers in real video, motion, recognition, stick model, video contents. I.
Keyphrases
human walking live video sequence human walker new synthesized video index term capture different motion knowledge-based framework vast application cyclic activity real-life video abstract extracting human representation structural information human body correlated temporal pattern system model video content stick model original video sequence real video body part articulated object cyclic motion
