Dynamic video anomaly detection and localization using sparse denoising autoencoders

Abstract

The emergence of novel techniques for automatic anomaly detection in surveillance videos has significantly reduced the burden of manual processing of large, continuous video streams. However, existing anomaly detection systems suffer from a high false-positive rate and also, are not real-time, which makes them practically redundant. Furthermore, their predefined feature selection techniques limit their application to specific cases. To overcome these shortcomings, a dynamic anomaly detection and localization system is proposed, which uses deep learning to automatically learn relevant features. In this technique, each video is represented as a group of cubic patches for identifying local and global anomalies. A unique sparse denoising autoencoder architecture is used, that significantly reduced the computation time and the number of false positives in frame-level anomaly detection by more than 2.5%. Experimental analysis on two benchmark data sets - UMN dataset and UCSD Pedestrian dataset, show that our algorithm outperforms the state-of-the-art models in terms of false positive rate, while also showing a significant reduction in computation time.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16

Notes

  1. 1.

    UCSD Pedestrian dataset http://www.svcl.ucsd.edu/projects/anomaly/dataset.htm

  2. 2.

    UMN Detection of Unusual Crowd Activity dataset http://mha.cs.umn.edu/proj_events.shtml

  3. 3.

    Structural Similarity Index Measurement. Online: http://live.ece.utexas.edu/research/quality/SSIM/

References

  1. 1.

    Adam A, Rivlin E, Shimshoni I, Reinitz D (2008) Robust real-time unusual event detection using multiple fixed-location monitors. IEEE Trans Pattern Anal Mach Intell 30(3):555–560

    Article  Google Scholar 

  2. 2.

    Aljawarneh S, Aldwairi M, Yassein MB (2017) Anomaly-based intrusion detection system through feature selection analysis and building hybrid efficient model. Journal of Computational Science. Elsevier

  3. 3.

    Aljawarneh SA, Vangipuram R, Puligadda VK, Vinjamuri J (2017) G-SPAMINE: An approach to discover temporal association patterns and trends in internet of things. Future Generation Computer Systems. Elsevier

  4. 4.

    Antić B, Ommer B (2011) Video parsing for abnormality detection. In: 2011 international conference on computer vision. IEEE, pp 2415–2422

  5. 5.

    Bertini M, Del Bimbo A, Seidenari L (2012) Multi-scale and real-time non-parametric approach for anomaly detection and localization. Comput Vis Image Underst 116(3):320–329

    Article  Google Scholar 

  6. 6.

    Cheng KW, Chen YT, Fang WH (2015) Video anomaly detection and localization using hierarchical feature representation and gaussian process regression. In: The IEEE conference on computer vision and pattern recognition (CVPR)

  7. 7.

    Cong Y, Yuan J, Liu J (2011) Sparse reconstruction cost for abnormal event detection. In: 2011 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 3449–3456

  8. 8.

    Goldberger J, Gordon S, Greenspan H (2003) An efficient image similarity measure based on approximations of kl-divergence between two gaussian mixtures. In: 2003. Proceedings. Ninth IEEE international conference on computer vision. IEEE, pp 487–493

  9. 9.

    He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision, pp 1026–1034

  10. 10.

    Jiang F, Yuan J, Tsaftaris SA, Katsaggelos AK (2011) Anomalous video event detection using spatiotemporal context. Comput Vis Image Underst 115 (3):323–333

    Article  Google Scholar 

  11. 11.

    Joseph E, Galeano P, Lillo RE (2013) The mahalanobis distance for functional data with applications to classification. arXiv:13044786

  12. 12.

    Kim J, Grauman K (2009) Observe locally, infer globally: a space-time mrf for detecting abnormal activities with incremental upyears. In: IEEE conference on computer vision and pattern recognition, 2009. CVPR 2009. IEEE, pp 2921–2928

  13. 13.

    Kong D, Gray D, Tao H (2005) Counting pedestrians in crowds using viewpoint invariant training. In: BMVC, Citeseer

  14. 14.

    Li C, Han Z, Ye Q, Jiao J (2013) Visual abnormal behavior detection based on trajectory sparse reconstruction analysis. Neurocomputing 119:94–100. doi:10.1016/j.neucom.2012.03.040. http://www.sciencedirect.com/science/article/pii/S0925231213000179, intelligent Processing Techniques for Semantic-based Image and Video Retrieval

    Article  Google Scholar 

  15. 15.

    Li N, Wu X, Xu D, Guo H, Feng W (2015) Spatio-temporal context analysis within video volumes for anomalous-event detection and localization. Neurocomputing 155:309–319

    Article  Google Scholar 

  16. 16.

    Li W, Mahadevan V, Vasconcelos N (2014) Anomaly detection and localization in crowded scenes. IEEE Trans Pattern Anal Mach Intell 36(1):18–32

    Article  Google Scholar 

  17. 17.

    Lippmann R (1987) An introduction to computing with neural nets. IEEE Assp magazine 4(2):4–22

    Article  Google Scholar 

  18. 18.

    Mahadevan V, Li W, Bhalodia V, Vasconcelos N (2010) Anomaly detection in crowded scenes. In: CVPR, vol 249, p 250

  19. 19.

    Mehran R, Oyama A, Shah M (2009) Abnormal crowd behavior detection using social force model. In: IEEE conference on computer vision and pattern recognition, 2009. CVPR 2009 . IEEE, pp 935–942

  20. 20.

    Mo X, Monga V, Bala R, Fan Z (2014) Adaptive sparse representations for video anomaly detection. IEEE Trans Circuits Syst Video Technol 24(4):631–645

    Article  Google Scholar 

  21. 21.

    Ng A (2011) Sparse autoencoder. CS294A lecture notes 72:1–19

    Google Scholar 

  22. 22.

    Radhakrishna V, Aljawarneh SA, Kumar P, Janaki V (2017) A novel fuzzy similarity measure and prevalence estimation approach for similarity profiled temporal association pattern mining. Future Generation Computer Systems. Elsevier

  23. 23.

    Reddy V, Sanderson C, Lovell BC (2011) Improved anomaly detection in crowded scenes via cell-based analysis of foreground speed, size and texture. In: CVPR 2011 WORKSHOPS. IEEE, pp 55–61

  24. 24.

    Roshtkhari MJ, Levine MD (2013) Online dominant and anomalous behavior detection in videos. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2611–2618

  25. 25.

    Sabokrou M, Fathy M, Hoseini M, Klette R (2015) Real-time anomaly detection and localization in crowded scenes. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 56–62

  26. 26.

    Saligrama V, Chen Z (2012) Video anomaly detection based on local statistical aggregates. In: 2012 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 2112–2119

  27. 27.

    Stauffer C, Grimson WEL (2000) Learning patterns of activity using real-time tracking. IEEE Trans Pattern Anal Mach Intell 22(8):747–757

    Article  Google Scholar 

  28. 28.

    Vincent P, Larochelle H, Bengio Y, Manzagol PA (2008) Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th international conference on machine learning, ACM, New York, NY, USA, ICML ’08. doi:10.1145/1390156.1390294, pp 1096–1103

  29. 29.

    Wang Z, Bovik A, Sheikh HR (2004) Image quality assessment from error measurement to structural similarity. IEEE Trans Image Process 13(4):600–612

    Article  Google Scholar 

  30. 30.

    Wu S, Moore BE, Shah M (2010) Chaotic invariants of lagrangian particle trajectories for anomaly detection in crowded scenes. IEEE

  31. 31.

    Xu D, Song R, Wu X, Li N, Feng W, Qian H (2014) Video anomaly detection based on a hierarchical activity discovery within spatio-temporal contexts. Neurocomputing 143:144–152

    Article  Google Scholar 

  32. 32.

    Xu D, Yan Y, Ricci E, Sebe N (2017) Detecting anomalous events in videos by learning deep representations of appearance and motion. Comput Vis Image Underst 156:117–127

    Article  Google Scholar 

  33. 33.

    Zhang Y, Lu H, Zhang L, Ruan X, Sakai S (2016) Video anomaly detection based on locality sensitive hashing filters. Pattern Recogn 59:302–311. doi:10.1016/j.patcog.2015.11.018

    Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Medhini G. Narasimhan.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Narasimhan, M.G., S., S.K. Dynamic video anomaly detection and localization using sparse denoising autoencoders. Multimed Tools Appl 77, 13173–13195 (2018). https://doi.org/10.1007/s11042-017-4940-2

Download citation

Keywords

  • Anomaly detection
  • Deep learning
  • Sparse autoencoders
  • Crowded scene parsing
  • Real-time systems
  • Unsupervised learning