Main Article Content

Meenal Suryakant Vatsaraj
Rajan Vishnu Parab
D S Bade


anomaly, artificial neural network (ANN), background subtraction, computational cost, Gaussian mixture model (GMM), histogram of oriented gradients (HOG), kernel density estimation (KDE), markov random field (MRF), region of interest (ROI).


Anomalous behavior detection and localization in videos of the crowded area that is specific from a dominant pattern are obtained. Appearance and motion information are taken into account to robustly identify different kinds of an anomaly considering a wide range of scenes. Our concept based on a histogram of oriented gradients and Markov random field easily captures varying dynamic of the crowded environment.

Histogram of oriented gradients along with well-known Markov random field will effectively recognize and characterizes each frame of each scene. Anomaly detection using artificial neural network consist both appearance and motion features which extract within spatio temporal domain of moving pixels that ensures robustness to local noise and thus increases accuracy in detection of a local anomaly with low computational cost.

To extract a region of interest we have to subtract background. Background subtraction is done by various methods like Weighted moving mean, Gaussian mixture model, Kernel density estimation.


Abstract 717 | PDF Downloads 49


[1] Andrei Zaharescu, Richard Wildes, “Anomalous Behaviour Detection Using Spatiotemporal Oriented Energies, Subset Inclusion Histogram Comparison and Event-Driven Processing,” CCV 2010, Part I, LNCS 6311, pp- 563–576, 2010.c Springer-Verlag Berlin Heidelberg 2010.

[2] B. E. Moore, M. Shah and S. Wu, “ Chaoticinvariants of lagrangian particle trajectories for anomaly detection in crowded scenes,” in Proc. IEEE Conference. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2010, pp- 2054–2060.

[3] Y. Cong, J. Yuan, and J. Liu, “ Sparse reconstruction cost for abnormal event detection,” in Proc. IEEE Conference Computer Vis. PatternRecognit. (CVPR), Jun. 2011, pp. 3449–3456.

[4] K. Nishino,L.Kratz , “Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models,” in Proc.IEEE Conference. Computer Vis. Pattern Recognit. (CVPR), Jun. 2009, pp. 1446–1453.

[5] J. Shi, C. Lu, and J. Jia, “Abnormal event detection at 150 FPS in MATLAB,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Dec. 2013, pp. 2720–2727.

[6] Jeisung Lee and Mignon Park, “An Adaptive Background Subtraction Method Based on Kernel Density Estimation,” Sensors 2012, 12, 12279-12300;

[7] A. Briassouli, V. Kaltsa, and I. Kompatsiaris, and M. G. Strintzis, “Swarm based motion features for anomaly detection in crowds,” in Proc. IEEEInt. Conference Image Process. (ICIP), Oct. 2014, pp. 2353–2357.

[8] A. Del Bue,M.Cristani, R. Raghavendra, and V. Murino, “ Optimizing interaction force for global anomaly detection in crowded scenes,” in Proc. IEEE Int. Conference Computer Vis. Workshops (ICCVW), Nov. 2011, pp. 136–143.

[9] M. Shah, A. Gritai ,andA. Basharat, ,“ Learning object motion patterns for anomaly detection and improved object detection,” in Proc. IEEEConference Computer Vis. Pattern Recognit. (CVPR), Jun. 2008, pp. 1–8.

[10] N. Conci ,H.Ullah, “ Crowd motion segmentation and anomaly detection via multi-label optimization,” in Proc. IEEE Int. Conference. PatternRecognit. Workshop (ICPRW), Nov. 2012.

[11] C. Fookes, D. Ryan,S.Sridharan and S. Denman, “Textures of optical flow for real-time anomaly detection in crowds,” in Proc. 8th IEEEInt. Conference. Adv. Video Signal-Based Surveill. (AVSS), Aug./Sep. 2011, pp. 230–235.

[12] T.Thenmozhi, Dr.A.M.Kalpana, “Detection and tracking of moving object based on background subtraction,” International Conference "Recent Innovation in Science, Technology and Management" (ICRISTM-16)at Indian Federation of United Nations Associations, New Delhi, India on 12 June 2016ISBN: 978-81-932712-3-0.

[13] R. Mehran, A. Oyama, and M. Shah, “Abnormal crowd behavior detection using social force model,” in Proc. IEEE Conference ComputerVis.PatternRecognit. (CVPR), Jun. 2009, pp. 935–942.

[14] V. Reddy, C. Sanderson, and B. C. Lovell, “Improved anomaly detection in crowded scenes via cell-based analysis of foreground speed, size and texture,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognition.Workshops (CVPRW), June. 2011, pp- 55–61.

[15] V. Mahadevan, W. Li, V. Bhalodia, and N. Vasconcelos, “Anomaly detection in crowded scenes,” in Proc. IEEE Conference Computer Vis. PatternRecognit. (CVPR), June. 2010, pp- 1975–1981.