Video Anomaly Detection Based on Statistic Feature of Optical Flow Block

Abstract

Abstract:

Abstract： An anomaly detection algorithm based on the statistic feature of optical flow block was proposed. First, the whole optical flow field of training video sequences were obtained. Then, each optical flow field was divided into blocks and each block was preprocessed in order to extract the statistic feature considering both magnitude and phase information of the block. The Gaussian mixture model (GMM) was employed to establish the probability model of normal behaviors by feeding the statistic feature into it. The abnormal degree of the optical flow block was judged by the output posterior probability of the GMM probabilistic model. The experimental results show that the method proposed considers both the consistency information of moving objects and the partial occlusion issue, at the same time, improves the accuracy of anomaly detection.

Key words: anomaly detection, optical flow block, statistic feature, preprocessing, Gaussian mixture model

CLC Number:

TP 391

YU Haoa，SUN Tanfenga,b，JIANG Xinghaoa,b. Video Anomaly Detection Based on Statistic Feature of Optical Flow Block[J]. Journal of Shanghai Jiaotong University, 2015, 49(08): 1199-1204.

References

［1］Stauffer C， Grimson W E L.Learning patterns of activity using realtime tracking［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence，2000，22(8)：747757.

［2］Morris B T，Trivedi M M.Learning, modeling and classification of vehicle track patterns from live video［J］. IEEE Transactions on Intelligent Transportation Systems，2008，9(3)：425437.

［3］Basharat A, Gritai A, Shah M.Learning object motion patterns for anomaly detection and improved object detection［C］∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Anchorage：IEEE， 2008： 18.

［4］Jiang F, Yuan J, Tsaftaris S A, et al. Video anomaly detection in spatiotemporal context［C］∥Proceedings of the International Conference on Image Processing. Hong Kong： IEEE， 2010： 705708.

［5］Zhang T, Lu H, Li S Z. Learning semantic scene models by object classification and trajectory clustering［C］∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Miami：IEEE，2009： 19401947.

［6］Mehran R, Oyama A, Shah M.Abnormal crowd behavior detection using social force model［C］∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Miami： IEEE， 2009： 935942.

［7］Mahadevan V, Li W, Bhalodia V, et al. Anomaly detection in crowded scenes［C］∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. San Francisco： IEEE， 2010： 19751981.

［8］Xu D, Wu X, Song D, et al. Hierarchical activity discovery within spatiotemporal context for video anomaly detection［C］∥Image Processing (ICIP), 2013 20th IEEE International Conference on. Melbourne： IEEE, 2013： 35973601.

［9］Liu C. Beyond pixels: Exploring new representations and applications for motion analysis［D］. Cambridge：Massachusetts Institute of Technology，2009.

［10］Reynolds D A, Quatieri T F, Dunn R B. Speaker verification using adapted Gaussian mixture models［J］. Digital signal processing，2000，10(1)：1941.

［11］Zivkovic Z.Improved adaptive Gaussian mixture model for background subtraction［C］∥Proceedings of the International Conference on Pattern Recognition. Cambridge： IEEE， 2004： 2831.

［12］Kim J， Grauman K.Observe locally, infer globally: A spacetime MRF for detecting abnormal activities with incremental updates［C］∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Miami： IEEE， 2009： 29212928.

[1]	Xiao Wenbo, Xiong Jiakai, Yu Lesheng, He Yinshui, Ma Guohong. Weld Defect Monitoring Based on Two-Stage Convolutional Neural Network [J]. J Shanghai Jiaotong Univ Sci, 2025, 30(2): 291-299.
[2]	HU Mingxuan, QIAO Jun, ZHANG Zhinan. Segmentation and Evaluation of Continuous Rehabilitation Exercises [J]. Journal of Shanghai Jiao Tong University, 2023, 57(5): 533-544.
[3]	ZHANG Wenan, GAO Weizhan, LIU Andong. Robot Skill Learning Based on Dynamic Motion Primitives and Adaptive Control [J]. Journal of Shanghai Jiao Tong University, 2023, 57(3): 354-365.
[4]	ZHANG Jian, HU Xiaofeng, ZHANG Yahui. Abnormal Detection Method of Tool Machining Monitoring Data Based on Self-Paced Learning [J]. Journal of Shanghai Jiao Tong University, 2023, 57(10): 1346-1354.
[5]	XU Yong, CAI Yunze, SONG Lin. Review of Research on Condition Assessment of Nuclear Power Plant Equipment Based on Data-Driven [J]. Journal of Shanghai Jiao Tong University, 2022, 56(3): 267-278.
[6]	ZHENG Dezhong, YANG Yuanyuan, XIE Zhe, NI Yangfan, LI Wentao. Data Splitting Method of Distance Metric Learning Based on Gaussian Mixed Model [J]. Journal of Shanghai Jiao Tong University, 2021, 55(2): 131-140.
[7]	JIA Xiaoli,JIANG Xiaobo,JIANG Sanxin，LIU Peilin. A Reconstruction Algorithm for Speech Compressive Sensing Using Structural Features [J]. Journal of Shanghai Jiaotong University, 2017, 51(9): 1111-1116.
[8]	CHENG Xiefeng,FU Nüting. A Review of Heart Sound Identification Recognition [J]. Journal of Shanghai Jiaotong University, 2014, 48(12): 1745-1750.
[9]	LV　Fu-Qiang-1 , WANG Hui-1, LIU Hong-2. Traffic Flow Background Detection Algorithm Based on Improved Gaussian Mixture Model [J]. Journal of Shanghai Jiaotong University, 2012, 46(12): 1920-1925.