Adaptive monitoring for video surveillance

Adaptability is one of the key issues in the important area of surveillance systems. Based on attention and sensor samples, the experiential sampling technique provides a general framework for analyzing video data. In this paper, we present a scheme for adaptive monitoring of surveillance objects by utilizing the feedback of the experiential sampling based video surveillance results to change the video camera parameters. Our framework first detects the moving objects in the surveillance video. We then analyze the output of this step to determine the state of the video camera settings. The relevant parameters of the video camera are continuously adjusted based on a proportional feedback control system. The fixed camera is thus adoptively tuned so as to obtain a good quality surveillance video output. We centrally frame the target object by doing panning and zooming operations. Moreover, we utilize the experiential sampling approach to capture the moving objects by utilizing the context which is a function of the current state of the environment as well as past experiences. This adds tremendous flexibility to the surveillance process which can be applied in a wide variety of monitoring situations.

[1]  Edward Y. Chang,et al.  Multi-camera spatio-temporal fusion and biased sequence-data learning for security surveillance , 2003, MULTIMEDIA '03.

[2]  Ramesh C. Jain,et al.  An architecture for multiple perspective interactive video , 1995, MULTIMEDIA '95.

[3]  Gian Luca Foresti,et al.  Multimedia Video-Based Surveillance Systems , 2000 .

[4]  Edward Y. Chang,et al.  Invariant feature extraction and biased statistical inference for video surveillance , 2003, Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance, 2003..

[5]  Ramesh Jain,et al.  Experiential Sampling for video surveillance , 2003, IWVS '03.

[6]  Simone Santini,et al.  A Multiple Perspective Interactive Video Architecture for VSAM , 1999 .

[7]  A. TUSTIN,et al.  Automatic Control Systems , 1950, Nature.

[8]  Mohan S. Kankanhalli,et al.  Detection and removal of lighting & shaking artifacts in home videos , 2002, MULTIMEDIA '02.

[9]  Mohan S. Kankanhalli,et al.  Experience based sampling technique for multimedia analysis , 2003, MULTIMEDIA '03.

[10]  Nikos Paragios,et al.  Video-Based Surveillance Systems , 2002, Springer US.

[11]  Gian Luca Foresti,et al.  Multimedia Video-Based Surveillance Systems: Requirements, Issues and Solutions , 2000 .

[12]  Carlo S. Regazzoni,et al.  Advanced Video-Based Surveillance Systems , 1998 .

[13]  N. Paragios,et al.  Video-Based Surveillance Systems: Computer Vision and Distributed Processing , 2001 .

[14]  Ramesh C. Jain.  Experiential computing , 2003, CACM.

[15]  Xing Chen,et al.  Calibrating pan-tilt cameras in wide-area surveillance networks , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.