MRF Model for Detecting Abnormal Activates in Crowded Environments

Authors

  • K. Poomala  SNS College of Technology, Coimbatore, Tamilnadu, India
  • J. Jayageetha  SNS College of Technology, Coimbatore, Tamilnadu, India

Keywords:

MRF, HOG, ROI

Abstract

This paper focus on detecting unusual activities in video. The analysis of motions and behaviours in crowded scenes constitutes a challenging task for traditional computer vision methods. To overcome this disadvantage there are different methods are used to detect the abnormalities in the video. This proposed method shows that a space-time MRF (Markov Random Field) model for detecting abnormal activities like bicycle passing through a crowd. This method not only localizes abnormal activities in crowded scenes, it can also capture the irregular interactions between local activities in a global sense. Histograms of Oriented Gradients (HOG) are used for capture the image from the particular video. The extraction of appearance characteristics in Region Of Interest (ROI) tracked over time using HOG descriptor. The robustness of this method in practical application can be understood by applying it on long surveillance videos.

References

  1. R. Raghavendra, A. Del Bue, M. Cristani, and V. Murino, "Optimizing interaction force for global anomaly detection in crowded scenes," in Proc. IEEE Int. Conf. Comput. Vis. Workshops (ICCVW), Nov. 2011, pp. 136–143.
  2. N. P. Cuntoor, B. Yegnanarayana, and R. Chellappa, "Activity modeling using event probability sequences," IEEE Trans. Image Process., vol. 17, no. 4, pp. 594–607, Apr. 2008.
  3. L. Wang, Y. Qiao, and X. Tang, "Latent hierarchical model of temporal structure for complex activity classification," IEEE Trans. Image Process., vol. 23, no. 2, pp. 810–822, Feb. 2014.
  4. W. Hu, X. Zhou, W. Li, W. Luo, X. Zhang, and S. Maybank, "Active contour-based visual tracking by integrating colours, shapes, and motions," IEEE Trans. Image Process., vol. 22, no. 5, pp. 1778–1792, May 2013.
  5. A. Basharat, A. Gritai, and M. Shah, "Learning object motion patterns for anomaly detection and improved object detection," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2008, pp. 1–8.
  6. C. Piciarelli, C. Micheloni, and G. L. Foresti, "Trajectory-based anomalous event detection," IEEE Trans. Circuits Syst. Video Technol., vol. 18, no. 11, pp. 1544–1554, Nov. 2008.
  7. D. Tran, J. Yuan, and D. Forsyth, "Video event detection: From subvolume localization to spatiotemporal path search," IEEE Trans. Pattern Anal. Mach. Intell., vol. 36, no. 2, pp. 404–416, Feb. 2014.
  8. S. Wu, B. E. Moore, and M. Shah, "Chaotic invariants of Lagrangian particle trajectories for anomaly detection in crowded scenes," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2010, pp. 2054–2060.
  9. J. C. Nascimento, M. A. T. Figueiredo, and J. S. Marques, "Activity recognition using a mixture of vector fields," IEEE Trans. Image Process., vol. 22, no. 5, pp. 1712–1725, May 2013.
  10. R. Mehran, A. Oyama, and M. Shah, "Abnormal crowd behaviour detection using social force model," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2009, pp. 935–942.

International Journal of Scientific Research in Science, Engineering and Technology

Downloads

Published

2017-12-31

Issue

Volume 2, Issue 2, March-April-2016

Section

Research Articles

License

Copyright (c) IJSRSET

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
K. Poomala, J. Jayageetha, " MRF Model for Detecting Abnormal Activates in Crowded Environments, International Journal of Scientific Research in Science, Engineering and Technology(IJSRSET), Print ISSN : 2395-1990, Online ISSN : 2394-4099, Volume 2, Issue 2, pp.112-115, March-April-2016.