A CNN Based Approach for Crowd Anomaly Detection


Kinjal Vishnuprasad Joshi
Narendra M Patel


Automatic Anomaly detection in a crowd scene is very significant because of more apprehension with people’s safety in a public place. Because of usefulness and complexity, currently, it is an open research area. In this work, a new Convolutional Neural Network (CNN) model is proposed to detect crowd anomaly. Experiments are carried out on two publicly available datasets. The performance is measured by Accuracy and Area Under the ROC Curve (AUC). The experimental results determine the efficacy of the proposed model.


How to Cite
Kinjal Vishnuprasad Joshi, & Narendra M Patel. (2021). A CNN Based Approach for Crowd Anomaly Detection. International Journal of Next-Generation Computing, 12(1), 01–11. https://doi.org/10.47164/ijngc.v12i1.185


  1. CemDirekoglu, MelikeSah, Noel E. O'Connor, ‘Abnormal Crowd Behavior Detection Using Novel Optical Flow-Based Features’, IEEE International Conference on Advanced Video and Signal Based Surveillance,2017
  2. TahjidAshfaqueMostafa, JiaUddin and Md. Haider Ali, ‘Abnormal Event Detection in Crowded Scenarios’, 3rd International Conference on Electrical Information and Communication Technology (EICT), 7-9 December 2017, Khulna, Bangladesh.
  3. Mehran R, Oyama A, Shah M., ‘Abnormal crowd behavior detection using social force model,’ IEEE Conference on Computer Vision and Pattern Recognition, 2009.
  4. CemDirekoglu, Melikesah, Noel E. O'Connor, ‘Abnormal crowd behavior detection using novel optical flow-based features’, 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), 2017
  5. S. Wu, H. S. Wong and Z. Yu, ‘A Bayesian Model for Crowd Escape Behavior Detection’ in IEEE Transactions on Circuits and Systems for Video Technology, 24(1):85– 98, January 2014.
  6. D. Chen and P. Huang, ‘Motion-based unusual event detection in human crowds’, in Journal of Visual Communication and Image Representation, 22(2), pages: 178-186, 2011
  7. S. Wu, B. E. Moore, M. Shah, ‘Chaotic Invariants of Lagrangian Particle Trajectories for Anomaly Detection in Crowded Scenes’. IEEE Conference on Computer Vision and Pattern Recognition, pages: 2054-2060, 2010.
  8. Y. Cong, J. Yuan and J. Liu, ‘Abnormal Event Detection in Crowded Scenes using Sparse Representation’, Elsevier Journal of Pattern Recognition, 46(7):1851-1864, 2013
  9. Halbe M., Vyas V., Vaidya Y.M. (2017), ‘Abnormal Crowd Behavior Detection Based on Combined Approach of Energy Model and Threshold’, In Shankar B., Ghosh K., Mandal D., Ray S., Zhang D., Pal S. (eds) Pattern Recognition and Machine Intelligence. PReMI 2017. Lecture Notes in Computer Science, vol 10597. Springer, Cham.
  10. Hu et al., ‘Abnormal event detection in crowded scenes using histogram of oriented contextual gradient descriptor’, EURASIP Journal on Advances in Signal Processing, 2018:54
  11. XuguangZhang, Qian Zhang, ShuoHu, ChunshengGuo and Hui Yu, ‘Energy Level-Based Abnormal Crowd Behavior Detection’, Sensors, MDPI,2018
  12. Yong Yin, Qiannan Liu and ShibiaoMao, ‘Global Anomaly Crowd Behavior Detection Using Crowd Behavior Feature Vector’ International Journal of Smart Home(SERSC) Vol. 9, No. 12, (2015), pp. 149-160
  13. Wu Peng, Xu Hongling, Li Wenlin and Song Wenlong, ‘Harris Scale-Invariant Corner Detection Algorithm Based on the Significant Region’, International Journal of Signal Processing, Image Processing and Pattern Recognition Vol.9, No.3 (2016), pp.413-420
  14. N. Dalal and B. Triggs, ‘Histograms of oriented gradients for human detection’, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), San Diego, CA, USA, 2005, pp. 886-893 vol. 1
  15. A. C. Davies, J. H. Yin, and S. A. Velastin, ‘Crowd monitoring using image processing’, IEE Electron. Commun. Eng. J., 1995, vol. 7, no. 1, pp.37–47
  16. David A. Forsyth and Jean Ponce, ‘Computer Vision A modern approach’, Pearson second Edition
  17. Mishra, S., Sarkar, U., Taraphder, S., Datta, S., Swain, D., & Saikhom, R. et al. ‘Multivariate Statistical Data Analysis- Principal Component Analysis (PCA)’, International Journal of Livestock Research, 7(5), 60-78
  18. Liton Chandra Paul, Abdulla Al Suman and Nahid Sultan, ‘Methodological Analysis of Principal Component Analysis (PCA) Method’, International Journal of Computational Engineering & Management, ISSN: 2230-7893, Vol. 16 Issue 2, March 2013
  19. Michael A. Nielsen, ‘Neural Networks and Deep Learning’, Determination Press,2015
  20. B. Zhan, D. N. Monekosso, P. Remagnino, S. A. Velastin, and L.-Q. Xu, ‘Crowd analysis: A survey’, Machine Vis. Applicat., 2008, vol. 19, no. 2, pp. 345– 357
  21. Unusual Crowd Activity Dataset by University of Minnesota, http://mha.cs.umn.edu./movies/crowdac-tivity-all.avi/
  22. G. Sreenu and M. A. SaleemDurai, ‘Intelligent video surveillance: a review through deep learning techniques for crowd analysis’, Journal of Big data-Springer,6:48,2019
  23. Gaurav Tripathi, Kuldeep Singh and Dinesh Kumar Vishwakarma, ‘Convolutional neural networks for crowd behaviour analysis: a survey’, Springer Nature March-2018
  24. Weixin Li, Vijay Mahadevan and NunoVasconcelos , ‘Anomaly Detection and Localization in Crowded Scenes’, IEEE Transactions On Pattern Analysis and Machine Intelligence, June-2013
  25. Teng Li, Huan Chang, Meng Wang, Bingbing Ni, Richang Hong, and Shuicheng Yan, ‘Crowded Scene Analysis: A Survey’, IEEE Transactions on Circuits and Systems for Video Technology, 2015
  26. Julio Cezar Silveira Jacques Junior, Soraia Raupp Musse, and CláudioRositoJung, ‘Crowd analysis using computer vision techniques’, IEEE Signal Processing Magazine, 2010, pp 1053-5888
  27. Y. Benabbas, N. Ihaddadene, and C. Djeraba, ‘Motion pattern extraction and event detection for automatic visual surveillance’, Journal on Image and Video Processing, vol. 7, pp. 1–15, 2011
  28. Kinjal V. Joshi, Narendra M Patel, Mehul B. Shah, ‘A Review on Crowd Analysis Techniques’, Journal of Artificial Intelligence Research and Advances, ISSN: 2395-6720, Vol 6, Issue 2, pp 119-126, August-2019
  29. C. Lu, J. Shi and J. Jia, ‘Abnormal Event Detection at 150 FPS in MATLAB’, 2013 IEEE International Conference on Computer Vision, Sydney, NSW, 2013, pp.2720-2727.
  30. Sabokrou, M., Fayyaz, M., Fathy, M., Klette, R, ‘Deep-cascade: cascading 3D deep neural networks for fast anomaly detection
  31. and localization in crowded scenes’, IEEE Trans. Image Process,26(4), 1992–2004 (2017)
  32. Ravanbakhsh, M., Nabi, M., Mousavi, H., Sangineto, E., Sebe, N, ‘Plug-and-play cnn for crowd motion analysis: an application in abnormal event detection’, arXiv preprint arXiv:1610.00307 (2016)
  33. Sabokrou, M., Fayyaz, M., Fathy, M., Moayedd, Z., Klette, R, ‘Fully convolutional neural network for fast anomaly detection in crowded scenes’, arXiv preprint arXiv:1609.00866 (2016)
  34. Feng, Y., Yuan, Y., Lu, X., ‘Learning deep event models for crowd anomaly detection’, Neurocomputing 219, 548–556 (2017)
  35. Zhou, S., Shen, W., Zeng, D., Fang, M., Wei, Y., Zhang, Z., ‘Spatial-temporal convolutional neural networks for anomaly detection and localization in crowded scenes’, Sig. Process. Image Commun. 47, 358–368 (2016)
  36. Smeureanu, S., Ionescu, R.T., Popescu, M., Alexe, B, ‘Deep appearance features for abnormal behavior detection in video’, In: Image Analysis and Processing—ICIAP 2017, Catania, Italy (2017)
  37. Sun, J., Shao, J., He, C, ‘Abnormal event detection for video surveillance using deep one-class learning’, Multimed.ToolsAppl. (2017). https://doi.org/10.1007/s11042-017-5244-2
  38. Hinami, R., Mei, T., Satoh, S, ‘Joint detection and recounting of abnormal events by learning deep generic knowledge’, arXivpreprint arXiv:1709.09121 (2017)
  39. A. Zaharescu and R.P. Wildes, “Anomalous Behaviour Detection using Spatiotemporal Oriented Energies,Subset Inclusion Histogram Comparison and Event-Driven Processing”, ECCV, 2010. http://vision.eecs.yorku.ca/research/anomalous-behaviour-data/
  40. Mahdyar Ravanbakhsh, Moin Nabi, Enver Sangineto, Lucio Marcenaro, Carlo Regazzoni, Nicu Sebe, “Abnormal event detection in videos using generative adversarial nets”, In Proceedings of the IEEE International Conference on Image Processing, 2017
  41. Glorot, Xavier, and Yoshua Bengio. "Understanding the difficulty of training deep feedforward neural networks." In Proceedings of the thirteenth international conference on artificial intelligence and statistics, 2010, pp. 249-256