Joint multitarget object tracking and interaction analysis by a probabilistic bio-inspired model

In this paper a joint human tracking and human-to-human interaction recognition system is proposed. While usually these two functions are performed separately, it will be shown that it is possible to improve the tracking performances if these functions are done jointly. For this purpose, a Bayesian tracking algorithm is coupled with a bio-inspired interaction analysis framework. The motion patterns of moving entities provided by the tracker are analyzed in order to recognize the current situation; causal relationships between interacting individuals in the environment are formulated in terms of probabilistic distributions that are used to cue the tracker in closed loop. The effectiveness of the proposed approach is demonstrated for a variety of image sequences.