A real-time algorithm for moving objects detection in video images

This paper addresses our proposed algorithm to automatically segment out moving objects in video images. The algorithm is based on the region-based frame difference and adjusted background subtraction. An adaptive threshold technique is employed to choose the threshold value to segment the moving foreground objects from the still background. The experimental results demonstrate that both the accuracy and processing speed are very promising. Furthermore, the algorithm is robust to the changes of lighting condition and can be applied for the practical use.

[1]  Kwang-Yeob Lee,et al.  Wavelet-based vehicle tracking for automatic traffic surveillance , 2001, Proceedings of IEEE Region 10 International Conference on Electrical and Electronic Technology. TENCON 2001 (Cat. No.01CH37239).

[2]  Larry S. Davis,et al.  W4: Real-Time Surveillance of People and Their Activities , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Rahul Sukthankar,et al.  Argus: the digital doorman , 2001, IEEE Intelligent Systems.

[4]  Yoshiaki Shirai,et al.  Object tracking in cluttered background based on optical flow and edges , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[5]  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).

[6]  Wang Peng,et al.  Real-time moving object detection for video monitoring systems , 2006 .