Abnormal Event Detection in Video Using Motion and Appearance Information

  • Neptalí Menejes PalominoEmail author
  • Guillermo Cámara Chávez
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10657)


This paper presents an approach for the detection and localization of abnormal events in pedestrian areas. The goal is to design a model to detect abnormal events in video sequences using motion and appearance information. Motion information is represented through the use of the velocity and acceleration of optical flow and the appearance information is represented by texture and optical flow gradient. Unlike literature methods, our proposed approach provides a general solution to detect both global and local abnormal events. Furthermore, in the detection stage, we propose a classification by local regions. Experimental results on UMN and UCSD datasets confirm that the detection accuracy of our method is comparable to state-of-the-art methods.


Abnormal event detection Video analysis Spatiotemporal feature extraction Video surveillance Computer vision 



This work was supported by grant 011-2013-FONDECYT (Master Program) from the National Council for Science, Technology and Technological Innovation (CONCYTEC-PERU).


  1. 1.
    Li, T., Chang, H., Wang, M., Ni, B., Hong, R., Yan, S.: Crowded scene analysis: a survey. In: TCSVT 2015, pp. 367–386. IEEE (2015)Google Scholar
  2. 2.
    Mehran, R., Oyama, A., Shah, M.: Abnormal crowd behavior detection using social force model. In: CVPR 2009, pp. 935–942. IEEE (2009)Google Scholar
  3. 3.
    Colque, R., Júnior, C., Schwartz, W.: Histograms of optical flow orientation and magnitude to detect anomalous events in videos. In: SIBGRAPI 2015 (2015)Google Scholar
  4. 4.
    Reddy, V., Sanderson, C.: Improved anomaly detection in crowded scenes via cell-based analysis of foreground speed, size and texture. In: CVPRW 2011 (2011)Google Scholar
  5. 5.
    Nallaivarothayan, H., Fookes, C., Denman, S.: An MRF based abnormal event detection approach using motion and appearance features. In: AVSS 2014 (2014)Google Scholar
  6. 6.
    Ryan, D., Denman, S., Fookes, C., Sridharan, S.: Textures of optical flow for real-time anomaly detection in crowds. In: AVSS 2011, pp. 230–235 (2011)Google Scholar
  7. 7.
    Wang, T., Snoussi, H.: Histograms of optical flow orientation for abnormal events detection. In: PETS 2013, pp. 45–52. IEEE (2013)Google Scholar
  8. 8.
    Cong, Y., Yuan, J., Liu, J.: Abnormal event detection in crowded scenes using sparse representation. Pattern Recogn. 46(7), 1851–1864 (2013)CrossRefGoogle Scholar
  9. 9.
    Wu, S., Wong, H.-S., et al.: A Bayesian model for crowd escape behavior detection. In: CSVT 2014, vol. 24, no. 1, 85–98. IEEE (2014)Google Scholar
  10. 10.
    Kratz, L., Nishino, K.: Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models. In: CVPR, pp. 1446–1453 (2009)Google Scholar
  11. 11.
    Mahadevan, V., Li, W., et al.: Anomaly detection in crowded scenes. In: CVPR 2010, pp. 1975–1981. IEEE (2010)Google Scholar
  12. 12.
    Raghavendra, R., Del Bue, A., Cristani, M., Murino, V.: Optimizing interaction force for global anomaly detection in crowded scenes. In: ICCV 2011 (2011)Google Scholar
  13. 13.
    Guler, S., Farrow, M.K.: Abandoned object detection in crowded places. In: Proceedings of the PETS, pp. 18–23. Citeseer (2006)Google Scholar
  14. 14.
    Gul, S., Meyer, J.T., Hellge, C., Schierl, T., Samek, W.: Hybrid video object tracking in H. 265/HEVC video streams. In: MMSP, pp. 1–5. IEEE (2016)Google Scholar
  15. 15.
    Ngo, D.V., Do, N.T., Nguyen, L.A.T.: Anomaly detection in video surveillance: a novel approach based on sub-trajectory. In: ICEIC, pp. 1–4. IEEE (2016)Google Scholar
  16. 16.
    Unusual crowd activity dataset of University of Minnesota.
  17. 17.
    Shi, Y., Gao, Y., Wang, R.: Real-time abnormal event detection in complicated scenes. In: ICPR 2010, pp. 3653–3656. IEEE (2010)Google Scholar
  18. 18.
    Xu, D., Ricci, E., Yan, Y., Song, J., Sebe, N.: Learning deep representations of appearance and motion for anomalous event detection (2015)Google Scholar
  19. 19.
    Ravanbakhsh, M., Nabi, M., Mousavi, H., Sangineto, E.: Plug-and-play CNN for crowd motion analysis: an application in abnormal event detection (2016)Google Scholar
  20. 20.
    Revathi, A.R., Kumar, D.: An efficient system for anomaly detection using deep learning classifier. Signal Image Video Process. 11, 1–9 (2016)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Neptalí Menejes Palomino
    • 1
    Email author
  • Guillermo Cámara Chávez
    • 2
  1. 1.Universidad Católica San PabloArequipaPeru
  2. 2.Computer Science DepartmentFederal University of Ouro PretoOuro PretoBrazil

Personalised recommendations