Automatic Intruder Detection and Tracking System with Pan-Tilt-Zoom Camera

We propose an automatic monitoring system which detects and tracks intruders, using a pan-tiltzoom camera. Detection is based on a background subtraction method which detects the difference between input image and continuously updated background images. Tracking is based on a newly developed algorithm incorporating two complementary methods: template matching and frame difference. When both methods are available, the template position is corrected with the frame difference data, enabling the robust tracking of intruders regardless of shape, aspect, and moving velocity. When either of the two methods is not available, the other method continues tracking alone till both methods are available again. Tracking mode is selected automatically according to preva.iling conditions.

[1]  Yoshiaki Shirai,et al.  Realtime multiple object tracking based on optical flows , 1995, Proceedings of 1995 IEEE International Conference on Robotics and Automation.

[2]  Masayuki Inaba,et al.  Robot vision system with a correlation chip for real-time tracking, optical flow and depth map generation , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[3]  Azriel Rosenfeld,et al.  Visual surveillance and monitoring , 1998 .

[4]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[5]  W. Eric L. Grimson,et al.  Using adaptive tracking to classify and monitor activities in a site , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).