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,...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 formu-lated 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.展开更多
In this paper, we investigate the interacting super-Brownian motion depending on population size. This process can be viewed as the high density limit of a sequence of particle systems with branching mechanism dependi...In this paper, we investigate the interacting super-Brownian motion depending on population size. This process can be viewed as the high density limit of a sequence of particle systems with branching mechanism depending on their population size. We will construct a limit function-valued dual process.展开更多
文摘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 formu-lated 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.
基金Foundation item： Supported by National Natural Science Foundation of China（A10071008） . Acknowledgements Here the author thank Professor Wang Zikun, Li Zhanbing and Li Zenghu sincerely for their guidance and encouragement.
文摘In this paper, we investigate the interacting super-Brownian motion depending on population size. This process can be viewed as the high density limit of a sequence of particle systems with branching mechanism depending on their population size. We will construct a limit function-valued dual process.
