Motion constraint Markov network model for multi-target tracking

A typical Markov network for modeling the interaction among targets can handle the error merge problem, but it suffers from the labeling problem due to the blind competition among collaborative trackers. In this paper, we propose a motion constraint Markov network model for multi-target tracking. By augmenting the typical Markov network with an ad hoc Markov chain which carries motion constraint prior, this proposed model can overcome the blind competition and direct the label to the corresponding target even in the case of severe occlusion. In addition, the motion constraint prior is formulated as a local potential function and can be easily incorporated in the joint distribution representation of the novel model. Experimental results demonstrate that our model is superior to other methods in solving the error merge and labeling problems simultaneously and efficiently.