Multi-view-based Cooperative Tracking of Multiple Human Objects in Cluttered Scenes

This paper presents a multi-view-based cooperative tracking of multiple human objects. Occlusion is one of the difficult problems for human object tracking in cluttered scenes. Based on the homographic relation between the two views, we proposed a so-called cooperative tracking which consists of particle filter tracking for the objects in different views. The multiple view tracking is modeled as different sequences of hidden process and observation. In addition, based on the interaction between targets, a hidden variable is added in to reveal the reliability of the tracking result in that specific view. With this hidden variable, the cooperative tracking allocates computational resources for tracking the objects in different views. Experimental results show the efficiency of the proposed method