Abnormal motion pattern detection in video sequences by an unsupervised approach
Article Sidebar
Main Article Content
Abstract
Identifying anomalous motion behavior in video sequences is a challenging task. Manual annotation of a large number of surveillance videos is time-consuming because of the limited human brain's visual attention. This work presents a new framework to detect abnormalities from unlabeled videos using motion patterns for the normal and abnormal event. This paper proposed an unsupervised hierarchical agglomerative clustering technique for finding the abnormal behavior motion patterns. Dense trajectories of feature points were extracted and grouped into feature points for different interval groups with characteristics of the feature points' motion speed. With results from partitioning interval groups by hierarchical clustering, anomalous motion patterns were localized in surveillance video sequences. We performed experiments on publicly available datasets containing different abnormal samples. The experimental results showed that the proposed framework achieved the highest frame-level accuracy of 96.68% for the UMN dataset. The experiment has achieved the highest rate of detection (up to 98.63%) for UCSD pedestrian datasets. The proposed framework has achieved outstanding performance in both pixel level and frame level evaluation.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
Al-Dhamari A, Sudirman R, Mahmood NH. Abnormal behavior detection in automated surveillance videos: A review. J Theor Appl Inform Tech. 2017;95(19):5245-63.
Brax C, Niklasson L, Smedberg M. Finding behavioural anomalies in public areas using video surveillance data. 2008 11th International conference on information fusion; 2008 Jun 30 - Jul 3; Cologne, Germany. New York: IEEE; 2008. p. 1-8.
Mu C, Xie J, Yan W, Liu T, Li P. A fast recognition algorithm for suspicious behavior in high definition videos. Multimed Syst. 2016;22:275-85.
Al-Dhamari A, Sudirman R, Mahmood NH, Khamis NH, Yahya A. Online video-based abnormal detection using highly motion techniques and statistical measures. Multimed Tool Appl. 2019;17:2039-47.
Wu S, Wong HS, Yu Z. A Bayesian model for crowd escape behavior detection. IEEE Trans Circ Syst Video Tech. 2014;24: 85-98.
Wu S, Moore BE, Shah M. Chaotic invariants of Lagrangian particle trajectories for anomaly detection in crowded scenes. 2010 IEEE computer society conference on computer vision and pattern recognition; 2010 Jun 13-18; San Francisco, USA. New York: IEEE; 2010. p. 2054-60.
Weixin Li, Mahadevan V, Vasconcelos N. Anomaly detection and localization in crowded scenes. IEEE Trans Pattern Anal Mach Intell. 2014;36:18-32.
Mahadevan V, Li W, Bhalodia V, Vasconcelos N. Anomaly detection in crowded scenes. 2010 IEEE computer society conference on computer vision and pattern recognition; 2010 Jun 13-18; San Francisco, USA. New York: IEEE; 2010. p. 1975-81.
Mehran R, Oyama A, Shah M. Abnormal crowd behavior detection using social force model. 2009 IEEE conference on computer vision and pattern recognition; 2009 Jun 20-25; Miami, USA. New York: IEEE; 2009. p. 935-42.
Cong Y, Yuan J, Liu J. Sparse reconstruction cost for abnormal event detection. 2011 IEEE Conference on computer vision and pattern recognition (CVPR); 2011 Jun 20-25; Colorado Springs, USA. New York: IEEE; 2011. p. 3449-56.
Lin H, Deng JD, Woodford BJ, Shahi A. Online weighted clustering for real-time abnormal event detection in video surveillance. Proceedings of the 24th ACM international conference on multimedia; 2016 Oct 15-19; Amsterdam, Netherlands. New York: ACM Press; 2016. p. 536-40.
Chen DY, Huang PC. Motion-based unusual event detection in human crowds. J Vis Comm Image Represent. 2011;22(2):178-86.
Fu Z, Hu W, Tan T. Similarity based vehicle trajectory clustering and anomaly detection. IEEE international conference on image processing; 2005 Sep 14; Genova, Italy. New York: IEEE; 2005. p. II-602.
Basharat A, Gritai A, Shah M. Learning object motion patterns for anomaly detection and improved object detection. 2008 IEEE conference on computer vision and pattern recognition; 2008 Jun 23-28; Anchorage, USA. New York: IEEE; 2008. p. 1-8.
Colque RM, Caetano C, de Andrade MT, Schwartz WR. Histograms of optical flow orientation and magnitude and entropy to detect anomalous events in videos. IEEE Trans Circ Syst Video Tech. 2017;27:673-82.
Li X, Li W, Liu B, Liu Q, Yu N. Object-oriented anomaly detection in surveillance videos. 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP); 2018 Apr 15-20; Calgary, Canada. New York: IEEE; 2018. p. 1907-11.
Antic B, Ommer B. Video parsing for abnormality detection. 2011 International conference on computer vision; 2011 Nov 6-13; Barcelona, Spain. New York: IEEE; 2011. p. 2415-22.
Pennisi A, Bloisi DD, Iocchi L. Online real-time crowd behavior detection in video sequences. Comput Vis Image Understand. 2016;144:166-76.
Wang H, Klaser A, Schmid C, Liu CL. Action recognition by dense trajectories. CVPR 2011; 2011 Jun 20-25; Colorado Springs, USA. New York: IEEE; 2011. p. 3169-76.
Abuolaim AA, Leow WK, Varadarajan J, Ahuja N. On the essence of unsupervised detection of anomalous event in surveillance videos. International conference on computer analysis of images and patterns; 2017 Aug 22-24; Ystad, Sweden. New York: Springer; 2017. p. 160-71.
Pattnaik M. Abnormal event detection in pedestrian pathway using GARCH model and MLP classifier. Int J Signal Image Sci. 2019;5:15.
Yu B, Liu Y, Sun Q. A content-adaptively sparse reconstruction method for abnormal events detection with low-rank property. IEEE Trans Syst Man Cybern Syst. 2017;47:704-16.
Qasim T, Bhatti N. A low dimensional descriptor for detection of anomalies in crowd videos. Math Comput Simulat. 2019;166:245-52.
Srinivasan A, Gnanavel VK. Multiple feature set with feature selection for anomaly search in videos using hybrid classification. Multimed Tool Appl. 2019;78:7713-25.
Wang H, Schmid C. Action recognition with improved trajectories. IEEE international conference on computer vision; 2013 Dec 1-8; Sydney, Australia. New York: IEEE; 2013.
Farneback G. Two-frame motion estimation based on polynomial expansion. 13th Scandinavian conference, SCIA; 2003 Jun 29 - Jul 2; Halmstad, Sweden. Berlin: Springer; 2003. p. 363-70.
Rowland T. Velocity Vector [Internet]. Mathworld; 2019 [cited 2021 Feb 1]. Available from: http://mathworld.wolfram.com/VelocityVector.html.
Dubrofsky E. Homography estimation. Vancouver: The University of British Columbia; 2009.
LaRose D. A fast, affordable system for augmented reality. Pittsburgh: Carnegie Mellon University; 1998.
Ongun C, Temizel A, Temizel TT. Local anomaly detection in crowded scenes using finite-time Lyapunov exponent based clustering. 2014 11th IEEE international conference on advanced video and signal based surveillance (AVSS); 2014 Aug 26-29; Seoul, Korea (South). New York: IEEE; 2014. p. 331-6.
Ionescu RT, Smeureanu S, Alexe B, Popescu M. Unmasking the abnormal events in video. 2017 IEEE international conference on computer vision (ICCV); 2017 Oct 22-29; Venice, Italy. New York: IEEE; 2017.