Abnormal behavior detection based on regional optical flow

被引：6
|
作者：
Du J.-H. [1 ]
Xu L. [1 ]
机构：
[1] College of Electrical Engineering, Zhejiang University
来源：
Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science) | 2011年 / 45卷 / 07期
关键词：
Abnormal behavior detection; Foreground extraction; Optical flow computation; Orientation histogram;
D O I：
10.3785/j.issn.1008-973X.2011.07.004
中图分类号：
学科分类号：
摘要：
A human abnormal behavior detecting approach was proposed based on optical flow features in the motion area in order to meet the needs of intelligent video surveillance. An improved model of mixture of Gaussians was proposed to indicate the variation of background pixels in order to increase the robustness against lighting changes and environmental disturbances and reliably extract the motion area. Then the background model was adaptively updated. Foreground was obtained from video sequences by background subtraction. The motion area was labeled as several regions of interest, and the optical flow features in each labeled region were obtained using the Lucas-Kanade algorithm. Amplitude-based weighted orientation histogram derived from the optical flow features was defined to measure the anomaly of human activity. Then the entropy of each labeled region was computed to recognize abnormal events. Experiments were conducted on various video datasets, and the results were presented to verify the effectiveness of the proposed scheme.
引用
收藏
页码：1161 / 1166
页数：5
相关论文
共 19 条
  • [1] Poppe R., Vision-based human motion analysis: An overview, Computer Vision and Image Understanding, 104, 2, pp. 4-18, (2007)
  • [2] Mitra S., Acharya T., Gesture recognition: A survey, IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 37, 3, pp. 311-324, (2007)
  • [3] Mecocci A., Pannozzo M., A completely autonomous system that learns anomalous movements in advanced videosurveillance applications, IEEE International Conference on Image Processing, (2005)
  • [4] Calderara S., Cucchiara R., Prati A., Detection of abnormal behaviors using a mixture of Von Mises distributions, IEEE Conference on Advanced Video and Signal Based Surveillance, pp. 141-146, (2007)
  • [5] Bouttefroy P.L.M., Bouzerdoum A., Phung S.L., Et al., Abnormal behavior detection using a multi-modal stochastic learning approach, International Conference on Intelligent Sensors, Sensor Networks and Information Processing, pp. 121-126, (2008)
  • [6] Tehrani M.A., Kleihorst R., Meijer P., Et al., Abnormal motion detection in a real-time smart camera system, 3rd ACM/IEEE International Conference on Distributed Smart Cameras, pp. 1-7, (2009)
  • [7] Datta A., Shah M., Lobo N.D.V., Person-on-person violence detection in video data, Proceedings of the 16th International Conference on Pattern Recognition, pp. 433-438, (2002)
  • [8] Chen Y.-F., Liang G.-Y., Lee K.-K., Et al., Abnormal behavior detection by multi-SVM-based Bayesian network, International Conference on Information Acquisition, pp. 298-303, (2007)
  • [9] Xiang T., Gong S.-G., Incremental and adaptive abnormal behavior detection, Computer Vision and Image Understanding, 111, 1, pp. 59-73, (2008)
  • [10] Fathi A., Mori G., Action recognition by learning mid-level motion features, IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, (2008)
12