Contents of this page are obsolete. This page is preserved and stored at this URL just from historical viewpoint. Original URL was http://www.mm.media.kyoto-u.ac.jp/members/kameda/...
Please visit www.kameda-lab.org for recent information. (2002/12/06, kameda@ieee.org)

Publication, Research, Docs and Info, KAMEDA


next up previous
Next: References Up: Three Dimensional Motion Estimation Previous: Experiment

Conclusion

In this paper, we propose a human motion estimation method using a difference image sequence. We classify a status of nodes in the model into three modes; moving mode, stationary mode, and occlusion mode. A node is labeled with one of three modes by considering the relationship between the difference image and the projected region of the part on the image plane. The process calculates joint angles by referring the modes of the nodes at each frame. Through the experiment, we showed that our method can keep tracking the parts of the human in spite of the occlusions.



Yoshinari Kameda
Mon Apr 7 14:56:47 JST 1997