MRF augmented particle filter tracker

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 objec...

Full description

Saved in:
Bibliographic Details
Published in2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) Vol. 2; pp. 1097 - 1103 vol. 2
Main Authors Wang, H.L., Cheong, L.-F.
Format Conference Proceeding
LanguageEnglish
Published IEEE 2005
Subjects
Application software
Bayesian methods
Computer vision
Particle filters
Particle tracking
Robustness
Sampling methods
Switches
Target recognition
Target tracking
Online AccessGet full text

Cover

More Information
Summary: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.
ISBN:0769523722
9780769523729
ISSN:1063-6919
DOI:10.1109/CVPR.2005.234