A novel particle filter based people tracking method through occlusion
Yuru Wang1, Wei Zhao, Jiafeng Liu, Xianglong Tang, Peng Liu
1Pattern Recognition Centre, School of Computer in Harbin Ins
Available Online December 2008.
- 10.2991/jcis.2008.67How to use a DOI?
- Object tracking, Particle Filter, Occlusion
A novel multi-regions based particle filters that effectively deals with occlusion problem in people tracking has been proposed in this paper. After locating multiple key regions, the algorithm uses several nearly independent particle filters (NIPF) to track each region which will be influenced by the proximity and/or behavior of other regions. Comparing with the tracking method based on independent particle filter, the proposed algorithm is more effective in solving long-time partial or total occlusion problem. And the performance advantage the nearly independent particle filters in comparison with a joint filter is significant. This is demonstrated by the experimental results.
- © 2008, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Yuru Wang AU - Wei Zhao AU - Jiafeng Liu AU - Xianglong Tang AU - Peng Liu PY - 2008/12 DA - 2008/12 TI - A novel particle filter based people tracking method through occlusion BT - Proceedings of the 11th Joint Conference on Information Sciences (JCIS 2008) PB - Atlantis Press SP - 395 EP - 401 SN - 1951-6851 UR - https://doi.org/10.2991/jcis.2008.67 DO - 10.2991/jcis.2008.67 ID - Wang2008/12 ER -