Anomaly detection method in video based on spatio-temporal surprise computation

doi:10.7523/j.issn.1002-1175.2013.01.013

Abstract

Abstract:

We propose an anomaly detection method in video based on Bayesian surprise computation. We use the block-matching motion estimation method to extract low-level motion features (such as magnitude and direction of motion) and then calculate multi-scale histogram of motion vector. We use both spatial surprise and temporal surprise to detect not only "individual abnormal behavior" but also "group abnormal behavior". Experimental results show that our algorithm is robust and applicable and it can be easily implemented.

Key words: visual attention model, video analysis, Bayesian theory of surprise, anomaly detection

CLC Number:

TP391.4

XIE Jin-Sheng, GUO Li, CHEN Yun-Bi, ZHAO Long. Anomaly detection method in video based on spatio-temporal surprise computation[J]. , 2013, 30(1): 83-89.

References

[1] Hu W M, Xiao X J, Fu Z Y,et al. A system for learning statistical motion patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28:1450-1464.

[2] Wang X G, Ma X X,Grimson W E L. Unsupervised activity perception in crowded andcomplicated scenes using hierarchical Bayesian models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009,31:539-555.

[3] Ali S, Shah M. Floor fields for tracking in high density crowd scenes[C]//Computer Vision-Eccv 2008. PtIi, Proceedings,2008,5303:1-14.

[4] Jiang F,Yuan J S,Tsaftaris Sotirios A, et al. Anomalous video event detection using spatiotemporal context[J].ComputerVision and Image Understanding,2011,115:323-333.

[5] Cong Y,Yuan J S,Liu J. Sparse reconstruction cost for abnormal event detection[C]//Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on. 2011:3449-3456.

[6] Mehran R, Oyama A,Shah M. Abnormal crowd behavior detection using social force model[C]//CVPR: 2009 Ieee Conference on Computer Vision and Pattern Recognition.2009 Vols, 1-4:935-942.

[7] Wu S D, Moore B E,Shah M. Chaotic invariants of lagrangian particle trajectories for anomaly detection in crowded scenes[C]//IEEE Conference on Computer Vision and Pattern Recognition (Cvpr). 2010:2054-2060.

[8] Mahadevan V, Li W X,Bhalodia V, et al. Anomaly detection in crowded scenes[C]//IEEE Conference on Computer Vision and Pattern Recognition (Cvpr). 2010:1975-1981.

[9] Adam A, Rivlin E, Shimshoni I, et al. Robust real-time unusual event detection using multiple fixed-location monitors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30:555-560.

[10] Grundmann M, Meier F, Essa I. 3D shape context and distance transform for action recognition[C]//19th International Conference on Pattern Recognition. 2008:1-4.

[11] Salve S G,Jondhale K C. Shape matching and object recognition using shape contexts[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24:509-522.

[12] Markou M,Singh S.Novelty detection:a review,part 1:statistical apprnaches[J].Signal Processing,2003,83 (12):2481-2497.

[13] Itti L, Baldi P. Bayesian surprise attracts human attention[J]. Advances in Neural Information Processing Systems,2005,19:547-554.

[14] Maier W,Mair E,Burschka D,et al. Visual homing and surprise detection for cognitive mobile robots using image-based environment representations[C]//ICRA: 2009 IEEE International Conference on Robotics and Automation. 2009,1-7:2320-2325.

[15] Unusual crowd activity dataset of University of Minnesota[DB/OL].[2011-09-20]. Artifical Intelligence, Robotics and Vision Laboratory, Department of Computer Science and Engineering University of Minnesota, http://mha.cs.umn.edu/movies/crowdactivity-all.avi.

[16] Jaechul Kim,Grauman K. Observe locally, infer globally: a space-time MRF for detecting abnormal activities with incremental updates[C]//CVPR: 2009 Ieee Conference on Computer Vision and Pattern Recognition. 2009,1-4:2913-2920.