Please use this identifier to cite or link to this item:
Title: MRF augmented particle filter tracker
Authors: Wang, H.L.
Cheong, L.-F. 
Issue Date: 2005
Citation: Wang, H.L.,Cheong, L.-F. (2005). MRF augmented particle filter tracker. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2 : 1097-1103. ScholarBank@NUS Repository.
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. © 2005 IEEE.
Source Title: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISBN: 0769523722
ISSN: 10636919
DOI: 10.1109/CVPR.2005.234
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.


checked on Jan 28, 2020

Page view(s)

checked on Jan 27, 2020

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.