Abnormal Motion Detection for Intelligent Video Surveillance

Abstract:

A method of abnormal motion detection for intelligent video surveillance is presented, which includes object intrusion detection, object overlong stay detection and object overpopulation detection. Background subtraction algorithm is used to detect moving objects in video streams. Kalman filter is applied for object tracking. By the construction of relation matrix, the tracking process is divided into five statuses for prediction and estimation, which are object disappearing, object separating, new object appearing, object sheltering and object matching. The object parameters and predictive information in the next frame which is used to track moving objects is established by Kalman filter. Then, three types of abnormal motion detection are implemented. The relative position of alarm area or guard line with the rectangle boxes of the moving objects is used to detect whether the object is invading. The existing time of the moving objects in monitor area is counted to detect whether the object is staying too long. Moving objects in the monitor area are classified and counted to detect whether the objects are too much. Alarm will be triggered when abnormal motion detection as defined is detected in the monitor area.

• Periodical: Applied Mechanics and Materials (Volumes 58-60)
• Pages: 2290-2295
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.58-60.2290
• Online since: June 2011
• Authors: Ruo Hong Huan, Xiao Mei Tang, Zhe Hu Wang, Qing Zhang Chen
• Keywords: Abnormal Motion Detection, Background Subtraction, Intelligent Video Surveillance, Kalman Filter (KF), Relation Matrix

References

[1] A. Wiliem, V. Madasu, W. Boles and P. Yarlagadda: Detecting uncommon trajectories, Digital Image Computing: Techniques and Applications (2008), pp.398-404.

DOI: 10.1109/dicta.2008.45

[2] W.M. Hu, T.N. Tan, L. Wang and S. Maybank: A survey on visual surveillance of object motion and behaviors, IEEE Transactions on Systems, Man, and Cybernetics—Part C: Applications and Reviews, Vol. 34 (2004), pp.334-352.

DOI: 10.1109/tsmcc.2004.829274

[3] B. Shoushtarian and H.E. Bez: A practical adaptive approach for dynamic background subtraction using an invariant colour model and object tracking, Pattern Recognition Letters, Vol. 26 (2005), pp.5-26.

DOI: 10.1016/j.patrec.2004.07.013

[4] Y. J. Han and R .A. Wagner: Efficient and fast parallel - connected component algorithm. Journal of the Association for Computing Machinery, Vol. 37 (1990), pp.626-642.

DOI: 10.1145/79147.214077

[5] G. Welch and G. Bishop: An introduction to the Kalman filter (2006).

[6] L. Marcenaro, M. Ferrari, L. Marchesotti and C.S. Reqazzoni: Multiple object tracking under heavy occlusions by using Kalman filters based on shape matching, Proceeding of International Conference on Image Processing, Vol. 3 (2002), pp.341-344.

DOI: 10.1109/icip.2002.1038975

[7] Q. Wan and Y.N. Wang: Research and implementation of detecting and tracking multiple moving objects method, Application Research Of Computers, Vol. 24 (2007), pp.199-202.

[8] Information on http: /www. cbsr. ia. ac. cn/china/Action%20Databases%20CH. asp.

[9] A. Lipton, H. Fujiyoshi and R. Patil: Moving object classification and tracking from real-time video, Proceeding of IEEE Workshop on Applications of Computer Vision, Princeton, NJ (1998), pp.8-14.

DOI: 10.1109/acv.1998.732851