Real-time cooperative multi-target tracking by dense communication among Active Vision Agents

Abstract

We have proposed a real-time multi-target tracking system by cooperative behaviors of Active Vision Agents (AVAs), where an AVA is a logical model of a network-connected computer with an active camera. All AVAs change their roles adaptively by negotiating with each other. The previous system, however, was unable to simultaneously track target objects that are larger in number than the AVAs. In this paper, we realize the increase in number of simultaneously trackable objects by improving cooperative tracking protocols in terms of the following two functions: (1) each AVA provides information of observed objects for several agencies (i.e., a group of AVAs that track the same target) and (2) each agency can receive information of its target also from AVAs tracking other objects. Experimental results demonstrate that our system can track multiple targets (larger in number than the cameras) simultaneously and robustly in real time.