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 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.