Moving Object Detection for Video Monitoring Systems

In this paper, we present a real-time algorithm for moving object segmentation from image sequence of video monitoring systems. We capture structural background variation into a datasheet which represent a background model for a long image sequence. Then we differentiate moving object from the background by background subtraction. Our method can handle scenes containing moving backgrounds or illumination variations, and it achieves robust detection for different types of videos. Experimental results demonstrate that the proposed method can update the background exactly and quickly along with the variation of illumination and the shadow can be eliminated effectively.

[1]  Manuele Bicego,et al.  Integrated region- and pixel-based approach to background modelling , 2002, Workshop on Motion and Video Computing, 2002. Proceedings..

[2]  Kentaro Toyama,et al.  Wallflower: principles and practice of background maintenance , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[3]  Larry S. Davis,et al.  Non-parametric Model for Background Subtraction , 2000, ECCV.

[4]  Fatih Porikli,et al.  Human Body Tracking by Adaptive Background Models and Mean-Shift Analysis , 2003 .

[5]  Alex Pentland,et al.  Pfinder: Real-Time Tracking of the Human Body , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Larry S. Davis,et al.  A Robust Background Subtraction and Shadow Detection , 1999 .