吉林大学学报(工学版) ›› 2013, Vol. 43 ›› Issue (06): 1644-1649.doi: 10.7964/jdxbgxb201306034

• paper • Previous Articles     Next Articles

Abnormal behavior detection based on weighted energy of optical flow

FU Bo1, LI Wen-hui1,2, CHEN Bo1, WANG Cong1,2, WANG Ying1,2   

  1. 1. College of Computer Science and Technology, Jilin University, Changchun 130012, China;
    2. State Key Laboratory of Automotive Simulation and Control, Jilin University, Changchun 130012, China
  • Received:2012-06-26 Online:2013-11-01 Published:2013-11-01

Abstract:

A human abnormal behavior detecting approach was proposed based on optical flow features in the motion area. An improved dual background model, which includes an adaptive running average background model and a HSV background model, was developed to indicate the variation of background pixels in order to increase the robustness against illustration change and environmental disturbance. The model can reliably extract the motion area. Foreground was obtained from video sequences by background subtraction. The motion area was labeled as several regions of interest, and the optical features in each labeled region were obtained using Lucas-Kanade algorithm. Amplitude based weighted unit energy derived from the optical flow features was defined to measure the anomaly of human activity. Experiments were conducted on various videos indoor and outdoor, and the results were presented to verify the effectiveness of the proposed scheme.

Key words: computer application, abnormal behavior detection, dual background modeling, unit optical flow energy

CLC Number: 

  • TP391

[1] Datta A, Shah M, da Vitoria Lobo N. Person-on-person violence detection in video data[C]//16th International Conference on Pattern Recognition,Quebec, Canada,2002:433-438.

[2] Felzenszwalb P F, Huttenlocher D P. Pictorial structure for object recognition[J]. International Journal of Computer Vision, 2005, 61(1):55-79.

[3] Xiang Tao, Gong Shao-gang. Incremental and adaptive abnormal behavior detection[J]. Computer Vision and Image Understanding, 2008, 111(1):59-73.

[4] Fathi A, Mori G. Action recognition by learning mid-level motion features[DB/OL].[2012-01-17]. http:[C]//www.cs.sfu.ca/~mori/research/papers/fathi_actionrecognition_cvpr08.pdf.

[5] Andriluka M, Roth S, Schiele B. Pictorial structures revisited. People detection and atriculated pose estimation[C]//IEEE Conference on Computer Vision and Pattern Recognition, Miami, USA, 2009:1014-1021.

[6] Ma G Y, Lin X Y. Typical sequences extraction and recognition[J]. Lecture Notes in Computer Science, 2004, 3058:60-71.

[7] Masoud O, Papanikolopoulos N. A method for human action recognition[J]. Image and Vision Computing, 2003, 21(8):729-743.

[8] Au C E, Skaff S, Clark J J. Anomaly detection for video surveillance application[C]//18th International Conference on Pattern Recognition, Hong Kong,China, 2006:888-891.

[9] Koller D, Weber J, Huang T, et al. Toward robust automatic traffic scene analysis in real-time video[C]//Proceedings of the 12th IAPR International Conference on Computer Vision & Image Processing,Australia,1994:126-131.

[10] 杜鉴豪,许力. 基于区域光流特征的异常行为检测[J]. 浙江大学学报:工学版, 2011, 45(7):1161-1166. Du Jian-hao, Xu Li. Abnormal behavior detection based on regional optical flow[J]. Journal of Zhejiang University (Engineering Science), 2011, 45(7): 1161-1166.

[1] LIU Fu,ZONG Yu-xuan,KANG Bing,ZHANG Yi-meng,LIN Cai-xia,ZHAO Hong-wei. Dorsal hand vein recognition system based on optimized texture features [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(6): 1844-1850.
[2] WANG Li-min,LIU Yang,SUN Ming-hui,LI Mei-hui. Ensemble of unrestricted K-dependence Bayesian classifiers based on Markov blanket [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(6): 1851-1858.
[3] JIN Shun-fu,WANG Bao-shuai,HAO Shan-shan,JIA Xiao-guang,HUO Zhan-qiang. Synchronous sleeping based energy saving strategy of reservation virtual machines in cloud data centers and its performance research [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(6): 1859-1866.
[4] ZHAO Dong,SUN Ming-yu,ZHU Jin-long,YU Fan-hua,LIU Guang-jie,CHEN Hui-ling. Improved moth-flame optimization method based on combination of particle swarm optimization and simplex method [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(6): 1867-1872.
[5] LIU En-ze,WU Wen-fu. Agricultural surface multiple feature decision fusion disease judgment algorithm based on machine vision [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(6): 1873-1878.
[6] OUYANG Dan-tong, FAN Qi. Clause-level context-aware open information extraction [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(5): 1563-1570.
[7] LIU Fu, LAN Xu-teng, HOU Tao, KANG Bing, LIU Yun, LIN Cai-xia. Metagenomic clustering method based on k-mer frequency optimization [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(5): 1593-1599.
[8] GUI Chun, HUANG Wang-xing. Network clustering method based on improved label propagation algorithm [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(5): 1600-1605.
[9] LIU Yuan-ning, LIU Shuai, ZHU Xiao-dong, CHEN Yi-hao, ZHENG Shao-ge, SHEN Chun-zhuang. LOG operator and adaptive optimization Gabor filtering for iris recognition [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(5): 1606-1613.
[10] CHE Xiang-jiu, WANG Li, GUO Xiao-xin. Improved boundary detection based on multi-scale cues fusion [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(5): 1621-1628.
[11] ZHAO Hong-wei, LIU Yu-qi, DONG Li-yan, WANG Yu, LIU Pei. Dynamic route optimization algorithm based on hybrid in ITS [J]. 吉林大学学报(工学版), 2018, 48(4): 1214-1223.
[12] HUANG Hui, FENG Xi-an, WEI Yan, XU Chi, CHEN Hui-ling. An intelligent system based on enhanced kernel extreme learning machine for choosing the second major [J]. 吉林大学学报(工学版), 2018, 48(4): 1224-1230.
[13] FU Wen-bo, ZHANG Jie, CHEN Yong-le. Network topology discovery algorithm against routing spoofing attack in Internet of things [J]. 吉林大学学报(工学版), 2018, 48(4): 1231-1236.
[14] CAO Jie, SU Zhe, LI Xiao-xu. Image annotation method based on Corr-LDA model [J]. 吉林大学学报(工学版), 2018, 48(4): 1237-1243.
[15] HOU Yong-hong, WANG Li-wei, XING Jia-ming. HTTP-based dynamic adaptive streaming video transmission algorithm [J]. 吉林大学学报(工学版), 2018, 48(4): 1244-1253.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!