Artificial Potential Field Based Cooperative Particle Filter for Multi-View Multi-Object Tracking

To continuously track the multiple occluded object in the crowded scene, we propose a new multi-view multi-object tracking method basing on artificial potential field and cooperative particle filter in which we combine the bottom-up and top-down tracking methods for better tracking results. After obtaining the accurate occupancy map through the multi-planar consistent constraint, we predict the tracking probability map via cooperation among multiple particle filters. The main point is that multiple particle filters´ cooperation is considered as the path planning and particles´ random shifting is guided by the artificial potential field. Comparative experimental results with the traditional blob-detection-tracking algorithm demonstrate the effectiveness and robustness of our method.