Agent-based active-vision system reconfiguration for autonomous surveillance of dynamic, multi-object environments

This paper presents a novel method for the coordinated selection and positioning of groups of active-vision cameras for the surveillance of an object-of-interest as it travels through a multi-object environment with an a priori unknown trajectory. Dynamic sensing-system reconfiguration is achieved through the use of multiple real and virtual agents. The proposed reconfiguration algorithm is implemented on an experimental prototype setup for automated facial recognition of a single subject in a cluttered environment.

[1]  Harry Wechsler,et al.  The FERET database and evaluation procedure for face-recognition algorithms , 1998, Image Vis. Comput..

[2]  Kazuhiko Sumi,et al.  A robust background subtraction method for changing background , 2000, Proceedings Fifth IEEE Workshop on Applications of Computer Vision.

[3]  O. Faugeras.  Three-dimensional computer vision: a geometric viewpoint , 1993 .

[4]  Avinash C. Kak,et al.  Spar: A Planner that Satisfies Operational and Geometric Goals in Uncertain Environments , 1990, AI Mag..

[5]  Henrik I. Christensen,et al.  Bayesian methods for interpretation and control in multiagent vision systems , 1992, Defense, Security, and Sensing.

[6]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[7]  Camillo J. Taylor,et al.  Dynamic Sensor Planning and Control for Optimally Tracking Targets , 2003, Int. J. Robotics Res..

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

[9]  Peter Kovesi,et al.  Automatic Sensor Placement from Vision Task Requirements , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Hong Zhang.  Two-dimensional optimal sensor placement , 1995, IEEE Trans. Syst. Man Cybern..

[11]  A. Pentland,et al.  Attention-driven Expression and Gesture Analysis in an Interactive Environment , 1995 .

[12]  Andrew M. Wallace,et al.  Model-based planning of optimal sensor placements for inspection , 1997, IEEE Trans. Robotics Autom..

[13]  Konstantinos A. Tarabanis,et al.  A survey of sensor planning in computer vision , 1995, IEEE Trans. Robotics Autom..

[14]  Takashi Matsuyama,et al.  Active Image Capturing and Dynamic Scene Visualization by Cooperative Distributed Vision , 1998, AMCP.

[15]  Yifan Chen,et al.  CAD-guided sensor planning for dimensional inspection in automotive manufacturing , 2003 .

[16]  Peter Struss,et al.  Directions in AI Research and Applications at Siemens Corporate Research and Development , 1990, AI Mag..

[17]  Roger Y. Tsai,et al.  Analytical characterization of the feature detectability constraints of resolution, focus, and field-of-view for vision sensor planning , 1994 .

[18]  Alex Pentland,et al.  Face recognition using eigenfaces , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[19]  Irfan Essa,et al.  Tracking Multiple People with Multiple Cameras , 1998 .

[20]  Mohamed S. Kamel,et al.  A coordination mechanism for model-based multi-sensor planning , 2002, Proceedings of the IEEE Internatinal Symposium on Intelligent Control.

[21]  Fuhua Cheng,et al.  Shadow generation using discretized shadow volume in angular coordinates , 2003, 11th Pacific Conference onComputer Graphics and Applications, 2003. Proceedings..

[22]  Yiming Ye,et al.  Sensor Planning for 3D Object Search, , 1999, Comput. Vis. Image Underst..

[23]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[24]  Roger Y. Tsai,et al.  Occlusion-Free Sensor Placement Planning , 1990 .

[25]  Enrico Grosso,et al.  Active vision-based face authentication , 2000, Image Vis. Comput..

[26]  Takashi Matsuyama,et al.  Real-time cooperative multi-target tracking by communicating active vision agents , 2002, Object recognition supported by user interaction for service robots.

[27]  Modesto Castrillón Santana,et al.  DESEO: An Active Vision System for Detection, Tracking and Recognition , 1999, ICVS.