2019, Volume 5, Issue 5
Engineering >> 2019, Volume 5, Issue 5 doi: 10.1016/j.eng.2019.02.008
AED-Net: An Abnormal Event Detection Network
a School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China
b Department of Electronic Engineering, Dalian Maritime University, Dalian 116026, China
c School of Instrumentation Science and Opto-electronic Engineering & International Research Institute for Multidisciplinary Science, Beihang University, Beijing 100191, China
d Institute Charles Delaunay-LM2S-UMR STMR 6281 CNRS, University of Technology of Troyes, Troyes 10010, France
Next Previous
Abstract
It has long been a challenging task to detect an anomaly in a crowded scene. In this paper, a self-supervised framework called the abnormal event detection network (AED-Net), which is composed of a principal component analysis network (PCAnet) and kernel principal component analysis (kPCA), is proposed to address this problem. Using surveillance video sequences of different scenes as raw data, the PCAnet is trained to extract high-level semantics of the crowd's situation. Next, kPCA, a one-class classifier, is trained to identify anomalies within the scene. In contrast to some prevailing deep learning methods, this framework is completely self-supervised because it utilizes only video sequences of a normal situation. Experiments in global and local abnormal event detection are carried out on Monitoring Human Activity dataset from University of Minnesota (UMN dataset) and Anomaly Detection dataset from University of California, San Diego (UCSD dataset), and competitive results that yield a better equal error rate (EER) and area under curve (AUC) than other state-of-the-art methods are observed. Furthermore, by adding a local response normalization (LRN) layer, we propose an improvement to the original AED-Net. The results demonstrate that this proposed version performs better by promoting the framework's generalization capacity.
Keywords
Abnormal events detection ; Abnormal event detection network ; Principal component analysis network ; Kernel principal component analysis
Figures
Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
References
[ 1 ] Kalal Z, Matas J, Mikolajczyk K. P–N learning: bootstrapping binary classifiers by structural constraints. In: Proceedings of the Computer Vision and Pattern Recognition; 2010 Jul 13–18; San Francisco, CA, USA. New York: IEEE; 2010. p. 49–56. link1
[ 2 ] Rui C, Martins P, Batista J. Exploiting the circulant structure of tracking-bydetection with kernels. In: Proceedings of the European Conference on Computer Vision; 2012 Oct 7–13; Florence, Italy. Berlin: Springer; 2012. p. 702–15. link1
[ 3 ] Zhang K, Zhang L, Yang MH. Fast compressive tracking. IEEE Trans Pattern Anal Mach Intell 2014;36(10):2002–15. link1
[ 4 ] Thapar D, Nigam A, Aggarwal D, Agarwal P. VGR-net: a view invariant gait recognition network. In: Proceedings of the IEEE International Conference on Identity, Security, and Behavior Analysis. 2018 Jan 11–12; Singapore. New York: IEEE; 2018. link1
[ 5 ] Wu Z, Huang Y, Wang L, Wang X, Tan T. A comprehensive study on cross-view gait based human identification with deep CNNs. IEEE Trans Pattern Anal Mach Intell 2017;39(2):209–26. link1
[ 6 ] Bojanowski P, Bach F, Laptev I, Ponce J, Schmid C, Sivic J. Finding actors and actions in movies. In: Proceedings of the IEEE International Conference on Computer Vision. 2013 Dec 1–8; Sydney, Australia. New York: IEEE; 2013. link1
[ 7 ] Cricri F, Roininen MJ, Leppanen J, Mate S, Curcio IDD, Uhlmann S, et al. Sport type classification of mobile videos. IEEE Trans Multimed 2014;16 (4):917–32. link1
[ 8 ] Wang T, Chen Y, Zhang M, Chen J, Snoussi H. Internal transfer learning for improving performance in human action recognition for small datasets. IEEE Access 2017;5:17627–33. link1
[ 9 ] Li W, Mahadevan V, Vasconcelos N. Anomaly detection and localization in crowded scenes. IEEE Trans Pattern Anal Mach Intell 2014;36(1):18–32. link1
[10] Wang T, Snoussi H. Detection of abnormal visual events via global optical flow orientation histogram. IEEE Trans Inf Forensics Security 2014;9 (6):988–98. link1
[11] Pan Y. Heading toward artificial intelligence 2.0. Engineering 2016;2 (4):409–13. link1
[12] Xing EP, Ho Q, Xie P, Wei D. Strategies and principles of distributed machine learning on big data. Engineering 2016;2(2):179–95. link1
[13] Wang T, Chen Y, Qiao M, Snoussi H. A fast and robust convolutional neural network-based defect detection model in product quality control. Int J Adv Manuf Technol 2018;94(9–12):3456–71. link1
[14] Chan TH, Jia K, Gao S, Lu J, Zeng Z, Ma Y. PCANet: a simple deep learning baseline for image classification? IEEE Trans Image Process 2015;24 (12):5017–32. link1
[15] Bao T, Karmoshi S, Ding C, Zhu M. Abnormal event detection and localization in crowded scenes based on PCANet. Multimedia Tools Appl 2017;76 (22):23213–24. link1
[16] Hoffmann H. Kernel PCA for novelty detection. Patt Recog 2007;40(3):863–74. link1
[17] University of Minnesota [Internet]. Detection of unusual crowd activity; 2006 [cited 2019 February 24]. Available from: http://mha.cs.umn.edu/proj_events. shtml. link1
[18] Mahadevan V, Li W, Bhalodia V, Vasconcelos N. Anomaly detection in crowded scenes. In: Proceedings of the Computer Vision and Pattern Recognition; 2010 Jun 13–18; San Francisco, CA, USA. New York: IEEE; 2010. link1
[19] Stauffer C, Grimson WEL. Learning patterns of activity using real-time tracking. Trans Pami 2000;22(8):747–57. link1
[20] Zhang T, Lu H, Li SZ. Learning semantic scene models by object classification and trajectory clustering. In: Proceedings of the 2009 IEEE Conference on the Computer Vision and Pattern Recognition; 2009 Jun 20–25; Miami, FL, USA. New York: IEEE; 2009. link1
[21] Siebel NT, Maybank SJ. Fusion of multiple tracking algorithms for robust people tracking. In: Proceedings of the European Conference on Computer Vision; 2002 May 28–31; Copenhagen, Denmark; 2002.
[22] Cui X, Liu Q, Gao M, Metaxas DN. Abnormal detection using interaction energy potentials. In: Proceedings of the Computer Vision and Pattern Recognition; 2011 Jun 20–25; Colorado Springs, CO, USA. New York: IEEE; 2011. link1
[23] Wu S, Moore BE, Shah M. Chaotic invariants of Lagrangian particle trajectories for anomaly detection in crowded scenes. In: Proceedings of the Computer Vision and Pattern Recognition; 2010 Jun 13–18; San Francisco, CA, USA. New York: IEEE; 2010. link1
[24] Khalid S. Activity classification and anomaly detection using m-mediods based modelling of motion patterns. Pattern Recognit 2010;43(10):3636–47. link1
[25] Rasheed N, Khan SA, Khalid A. Tracking and abnormal behavior detection in video surveillance using optical flow and neural networks. In: Proceedings of the 28th International Conference on Advanced Information Networking and Applications Workshops; 2014 May 13–16; Victoria, BC, Canada. New York: IEEE; 2014. link1
[26] Zhang Y, Qin L, Ji R, Yao H, Huang Q. Social attribute-aware force model: exploiting richness of interaction for abnormal crowd detection. IEEE Trans Circ Syst Video Tech 2015;25(7):1231–45. link1
[27] Yuan Y, Fang J, Wang Q. Online anomaly detection in crowd scenes via structure analysis. IEEE Trans Cybern 2015;45(3):548–61. link1
[28] Wang T, Qiao M, Zhu A, Niu Y, Li C, Snoussi H. Abnormal event detection via covariance matrix for optical flow based feature. Multimedia Tools Appl 2018;77(13):17375–95. link1
[29] Benezeth Y, Jodoin PM, Saligrama V, Rosenberger C. Abnormal events detection based on spatio-temporal co-occurrences. In: Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition; 2009 Jun 20–25; Miami, FL, USA. New York: IEEE; 2009. link1
[30] Benezeth Y, Jodoin PM, Saligrama V. Abnormality detection using low-level cooccurring events. Pattern Recognit Lett 2011;32(3):423–31. link1
[31] Jiménez-Hernández H, González-Barbosa JJ, Garcia-Ramírez T. Detecting abnormal vehicular dynamics at intersections based on an unsupervised learning approach and a stochastic model. Sensors 2010;10(8):7576–601. link1
[32] Kosmopoulos D, Chatzis SP. Robust visual behavior recognition. IEEE Signal Process Mag 2010;27(5):34–45. link1
[33] Adam A, Rivlin E, Shimshoni I, Reinitz D. Robust real-time unusual event detection using multiple fixed-location monitors. IEEE Trans Pattern Anal Mach Intell 2008;30(3):555–60. link1
[34] Cong Y, Yuan J, Liu J. Sparse reconstruction cost for abnormal event detection. In: Proceedings of the Computer Vision and Pattern Recognition; 2011 Jun 20– 25; Colorado Springs, CO, USA. New York: IEEE; 2011. p. 3449–56. link1
[35] Zhao B, Li F, Xing EP. Online detection of unusual events in videos via dynamic sparse coding. In: Proceedings of the 24th IEEE Conference on Computer Vision and Pattern Recognition. 2011 Jun 20–25; Colorado Springs, CO, USA. New York: IEEE; 2011. p. 3313–20. link1
[36] Mehran R, Oyama A, Shah M. Abnormal crowd behavior detection using social force model. In: Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. 2009 Jun 20–25; Miami, FL, USA. New York: IEEE; 2009. link1
[37] Bhatnagar G, Wu QMJ, Raman B. Discrete fractional wavelet transform and its application to multiple encryption. Inform Sci 2013;223:297–316. link1
[38] You X, Du L, Cheung Y, Chen Q. A blind watermarking scheme using new nontensor product wavelet filter banks. IEEE Trans Image Process 2010;19 (12):3271–84. link1
[39] Kemmler M, Rodner E, Wacker ES, Denzler J. One-class classification with Gaussian processes. Patt Recog 2013;46(12):3507–18. link1
[40] Burton A, Radford J. Thinking in perspective: critical essays in the study of thought processes. North Yorkshire: Methuen; 1978. link1
[41] Horn BK, Schunck BG. Determining optical flow. Artif Intell 1981;17(1– 3):185–203. link1
[42] Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift. 2015. arXiv:1502.03167.
[43] Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems; 2012 Dec 3–6; Lake Tahoe, NV, USA. New York: ACM; 2012. link1
京公网安备 11010502051620号
