Skip to main content
SpringerLink
Log in

Abnormal behavior detection in videos using deep learning

  • Published:
Cluster Computing Aims and scope Submit manuscript

Abstract

A new method for abnormal behavior detection is proposed using deep learning. Two SDAEs are utilized to automatically learn appearance feature and motion feature respectively, which are constrained in the space–time volume along dense trajectories that carry rich motion information to reduce the computational complexity. The vision words are exploited to describe behavior by the bag of words, and in order to reduce feature dimensions, the Agglomerative Information Bottleneck approach is used for vocabulary compression. An adaptive feature fusion method is adopted to enhance the discriminating power of these features. A sparse representation is exploited to abnormal behavior detection, which improve the detection accuracy. The proposed method is verified on the public dataset BEHAVE and BOSS and the results indicate the effectiveness of the proposed method.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Piciarelli, C., Foresti, G.L.: Trajectory-based anomalous event detection. IEEE Trans. Circ. Syst. Video Technol. 18(11), 1544–1554 (2008)

    Article  Google Scholar 

  2. Cosar, S., Donatiello, G., Bogorny, V., et al.: Toward abnormal trajectory and event detection in video surveillance. IEEE Trans. Circ. Syst. Video Technol. 27(3), 683–695 (2017)

    Article  Google Scholar 

  3. Yang, W.Q., Gao, Y., Cao, L.B.: TRASMIL: a local anomaly detection framework based on trajectory segmentation and multi-instance learning. Comput. Vis. Image Underst. 117(10), 1273–1286 (2013)

    Article  Google Scholar 

  4. Li, C., Han, Z., Ye, Q., Jiao, J.: Visual abnormal behavior detection based on trajectory sparse reconstruction analysis. Neurocomputing 119(7), 94–100 (2013)

    Article  Google Scholar 

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

    Article  Google Scholar 

  6. Kang, K., Liu, W.B., Xing, W.W.: Motion pattern study and analysis from video monitoring trajectory. IEICE Trans. Inf. Syst. 6, 1574–1582 (2014)

    Article  Google Scholar 

  7. Bera, A.T., Kim, S., Manocha, D.: Realtime anomaly detection using trajectory-level crowd behavior learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 50–57. IEEE, Las Vegas (2016)

  8. Benezeth, Y., Jodin, P., Saligrama, V.: Abnormal events detection based on spatio-temporal co-occurrences. In: IEEE Computer Vision and Pattern Recognition, pp. 2458–2465. IEEE, Miami Beach (2009)

  9. Cong, Y., Yuan, J., Liu, J.: Sparse reconstruction cost for abnormal event detection. In: IEEE Computer Vision and Pattern Recognition, pp. 3449–3456. IEEE, Colorado Springs (2011)

  10. Kim, J., Grauman, K.: Observe locally, infer globally: a space-time MRF for detecting abnormal activities with incremental updates. In: IEEE Computer Vision and Pattern Recognition, pp. 2913–2920. IEEE, Miami Beach (2009)

  11. Saligrama, V., Chen, Z.: Video anomaly detection based on local statistical aggregates. In: IEEE Computer Vision and Pattern Recognition, pp. 2112–2119. IEEE, Providence (2012)

  12. Reddy, V., Sanderson, C., Lovell, B.C.: Improved anomaly detection in crowded scenes via cell-based analysis of foreground speed, size and texture. In: IEEE Computer Vision and Pattern Recognition, pp. 55–61. IEEE, Colorado Springs (2011)

  13. Zhao, B., Li, F.F., Xing, E.: Online detection of unusual events in videos via dynamic sparse coding. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3313–3320. IEEE, Colorado Springs (2011)

  14. Nallaivarothayan, H., Fookes, C., Denman, S.: An MRF based abnormal event detection approach using motion and appearance features. In: IEEE International Conference on Advanced Video and Signal based Surveillance, pp. 343–348. IEEE, Seoul (2014)

  15. Wang, Q., Ma, Q., Luo, C.H., et al.: Hybrid histogram of oriented optical flow for abnormal behavior detection in crowd scenes. Int. J. Pattern Recognit Artif Intell. 30(2), 1655007 (2016)

    Article  MathSciNet  Google Scholar 

  16. Zhang, Y., Lu, H.C., Zhang, L.H., et al.: Combining motion and appearance cues for anomaly detection. Pattern Recognit. 51, 443–452 (2016)

    Article  Google Scholar 

  17. Mehran, R., Oyama, A., Shah, M.: Abnormal crowd behavior detection using social force model. In: CVPR, pp. 905–912. IEEE Computer Society, Miami Beach (2009)

  18. Xu, D., Ricci, E.: Learning deep representations of appearance and motion for anomalous event detection. In: British Machine Vision Conference, pp. 1–12. Spring, Swansea (2015)

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

    Article  Google Scholar 

  20. Zhou, S.F., Shen, W., Zeng, D., et al.: Spatial-temporal convolutional neural networks for anomaly detection and localization in crowded scenes. Signal Process. Image Commun. 47, 358–368 (2016)

    Article  Google Scholar 

  21. Hu, X., Hu, S.Q., Huang, Y.P., et al.: Video anomaly detection using deep incremental slow feature analysis network. IET Comput. Vis. 10(4), 258–267 (2016)

    Article  Google Scholar 

  22. Feng, Y.C., Yuan, Y., Lu, X.Q.: Learning deep event models for crowd anomaly detection. Neurocomputing 219, 548–556 (2017)

    Article  Google Scholar 

  23. Sabokrou, M., Fayyaz, M., Fathy, M.: Deep-cascade: cascading 3D deep neural networks for fast anomaly detection and localization in crowded scenes. IEEE Trans. Image Process. 26(4), 1992–2004 (2017)

    Article  MathSciNet  Google Scholar 

  24. Erfani, S.M., Rajsegarar, S., Karunasekera, S., et al.: High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning. Pattern Recognit. 58, 121–134 (2016)

    Article  Google Scholar 

  25. Zhu, F., Shao, L., Xie, J., et al.: From handcrafted to learned representations for human action recognition: a survey. Image Vis. Comput. 55(1), 42–52 (2016)

    Article  Google Scholar 

  26. Wang, H., Schmid, C.: Action recognition with improved trajectories. In: IEEE International Conference on Computer Vision, pp. 3551–3558. IEEE, Sydney (2013)

  27. Zeng, H., Ma, K.K., Wang, C., et al.: SIFT-flow-based color correction for multi-view video. Signal Process. Image Commun. 36, 53–62 (2015)

    Article  Google Scholar 

  28. Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.: Extracting and composing robust features with denoising autoencoders. In: ICML (2008)

  29. Chakraborty, B., Holte, M., Moeslund, T., Gonzàlez, J.: Selective spatio-temporal interest points. Comput. Vis. Image Underst. 116, 396–410 (2012)

    Article  Google Scholar 

  30. Yan, S.C., Xu, D., Zhang, B.Y.: Graph embedding and extensions: a general framework for dimensionality reduction. IEEE Trans. Pattern Anal. Mach. Intell. 29(1), 40–51 (2007)

    Article  Google Scholar 

  31. Yan, S., Xu, D., Zhang, B., Zhang, H., Yang, Q., Lin, S.: Graph embedding and extensions: a general framework for dimensionality reduction. IEEE Trans. Pattern Anal. Mach. Intell. 29, 40–51 (2007)

    Article  Google Scholar 

  32. Tropp, J.A., Gilbert, C.: Signal recovery from random measurements via orthogonal matching pursuit. IEEE Trans. Inf. Theory 53, 4655–4666 (2007)

    Article  MathSciNet  Google Scholar 

  33. Aharon, M., Elad, M., Bruckstein, A.: SVDD: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans. Signal Proc. 54(11), 4311–4322 (2006)

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by the National Natural Science Foundation of China (Grant No. 51678075), the Science and Technology Project of Hunan (Grant No. 2017GK2271).

Author information

Authors and Affiliations

  1. Zhongshan Institute, University of Electronics Science and Technology, Zhongshan, 528402, China

    Jun Wang

  2. School of Information Science and Engineering, Central South University, Changsha, 410075, China

    Limin Xia

Authors
  1. Jun Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Limin Xia
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Limin Xia.

Ethics declarations

Conflict of interest

The authors declare that there is no conflict of interests regarding the publication of this paper (such as financial gain).

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, J., Xia, L. Abnormal behavior detection in videos using deep learning. Cluster Comput 22 (Suppl 4), 9229–9239 (2019). https://doi.org/10.1007/s10586-018-2114-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10586-018-2114-2

Keywords

Search

Navigation