|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
| ASCII Text | x | ||
| Naoto Date, Hiromasa Yoshimoto, Daisaku Arita, Satoshi Yonemoto, Rin-ichiro Taniguchi, "Performance Evaluation of Vision-Based Real-Time Motion Capture," Parallel and Distributed Processing Symposium, International, pp. 234, International Parallel and Distributed Processing Symposium (IPDPS'03), 2003. | |||
| BibTex | x | ||
| @article{ 10.1109/IPDPS.2003.1213427, author = {Naoto Date and Hiromasa Yoshimoto and Daisaku Arita and Satoshi Yonemoto and Rin-ichiro Taniguchi}, title = {Performance Evaluation of Vision-Based Real-Time Motion Capture}, journal ={Parallel and Distributed Processing Symposium, International}, volume = {0}, year = {2003}, issn = {1530-2075}, pages = {234}, doi = {http://doi.ieeecomputersociety.org/10.1109/IPDPS.2003.1213427}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - CONF JO - Parallel and Distributed Processing Symposium, International TI - Performance Evaluation of Vision-Based Real-Time Motion Capture SN - 1530-2075 SP EP A1 - Naoto Date, A1 - Hiromasa Yoshimoto, A1 - Daisaku Arita, A1 - Satoshi Yonemoto, A1 - Rin-ichiro Taniguchi, PY - 2003 KW - null VL - 0 JA - Parallel and Distributed Processing Symposium, International ER - | |||
In this paper, we discuss a vision-based real-time motion capture system, which is constructed on a PC-cluster. Vision-based motion capture is a merit that it does not impose any physical restrictions on humans, which provides a natural way of measuring human motion. However, there are several issues to be solved, which are robust estimation of human motion from limited number of visual cues, computation cost of the estimation algorithm.
To deal with these issues, we have developed multi-view-based algorithms using multiple cameras and we have implemented the algorithms on a PC-cluster to solve the computation problem. In this paper, we present our experimental study on vision-based real-time motion capture with emphasis on 3D human posture estimation.