DocumentCode :
3549213
Title :
MRF augmented particle filter tracker
Author :
Wang, Hee Lin ; Cheong, Loong-Fah
Author_Institution :
Nat. Univ. of Singapore, Singapore
Volume :
2
fYear :
2005
fDate :
20-25 June 2005
Firstpage :
1097
Abstract :
In particle filter trackers, the object a posteriori distribution is severely distorted under more challenging situations like occlusion. To overcome the problem, this paper proposes a principled manner of augmenting the particle filter algorithm with an MRF based representation of the tracked object within a dynamic Bayesian framework, where the object is transformed into a composite of multiple MRF regions. This results in more accurate modeling, thus improving the tracking performance. Additionally, Metropolis based sampling of the regions enhances the tracker with an adaptive ability. Finally, the resultant generative model provides a natural framework to integrate multiple cues. Experiments show good tracking results for challenging situations.
Keywords :
Markov processes; filtering theory; image enhancement; image representation; image sampling; object detection; tracking; MRF augmented particle filter tracker; Markov random field; dynamic Bayesian framework; image representation; image sampling; object tracking; occlusion; particle filter algorithm; Application software; Bayesian methods; Computer vision; Particle filters; Particle tracking; Robustness; Sampling methods; Switches; Target recognition; Target tracking;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on
ISSN :
1063-6919
Print_ISBN :
0-7695-2372-2
Type :
conf
DOI :
10.1109/CVPR.2005.234
Filename :
1467565
Link To Document :
بازگشت