Real-time cooperative multi-target tracking by communicating active vision agents

W e present a real-time cooperative multitarget tracking system. The system consists of a group of Active Vision Agents (AVAs), where an AVA i s a logical model of a network-connected computer with a n active camera. All AVAs cooperatively track their target objects by dynamically exchanging object i n f o m a tion with each other. I n this paper, we address the technologies employed in the system and demonstrate their effectiveness.

[1]  Takashi Matsuyama,et al.  Dynamic memory: architecture for real time integration of visual perception, camera action, and network communication , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[2]  Takashi Matsuyama.  Cooperative Distributed Vision: Dynamic Integration of Visual Perception, Action, and Communication , 1999, DAGM-Symposium.

[3]  Victor R. Lesser,et al.  Distributed sensor network for real time tracking , 2001, AGENTS '01.

[4]  Shuichi Nishio,et al.  Tracking of Vehicles at an Intersection by Integration of Multiple Image Sensors , 1992, MVA.

[5]  N. Atsushi,et al.  Tracking multiple people using distributed vision systems , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[6]  Gideon P. Stein,et al.  Tracking from multiple view points: Self-calibration of space and time , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).