Using Conditional Random Field for Crowd Behavior Analysis

  • Saira Saleem Pathan
  • Ayoub Al-Hamadi
  • Bernd Michaelis
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6468)


The governing behaviors of individuals in crowded places offer unique and difficult challenges. In this paper, a novel framework is proposed to investigate the crowd behaviors and to localize the anomalous behaviors. Novelty of the proposed approach can be revealed in three aspects. First, we introduce block-clips by sectioning video segments into non-overlapping patches to marginalize the arbitrarily complicated dense flow field. Second, flow field is treated as a 2d distribution of samples in block-clips, which is parameterized by using mixtures of Gaussian keeping the generality intact. The parameters of each Gaussian model, particularly mean values are transformed into a sequence of Gaussian mean densities for each block-clip namely a sequence of latent-words. A bank of Conditional Random Field model is employed, one for each block-clip, which is learned from the sequence of latent-words and classifies each block-clip as normal and abnormal. Experiments are conducted on two challenging benchmark datasets PETS 2009 and University of Minnesota and results show that our method achieves higher accuracy in behavior detection and can effectively localize specific and overall anomalies. Besides, a comparative analysis is presented with similar approaches which demonstrates the dominating performance of our approach.


Video Sequence Gaussian Mixture Model Conditional Random Field Video Segment Label Sequence 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Zhan, B., Monekosso, D., Remagnino, P., Velastin, S., Xu, L.: Crowd analysis: a survey. Machine Vision Application 19, 345–357 (2008)CrossRefGoogle Scholar
  2. 2.
    Boghossian, A., Velastin, A.: Motion-based machine vision techniques for the management of large crowds. In: Proceedings of IEEE International Conference on Electronics, Circuits and Systems, vol. 2, pp. 961–964 (2002)Google Scholar
  3. 3.
    Maurin, B., Masoud, O., Papanikolopoulos, N.: Monitoring crowded traffic scenes. In: IEEE International Conference on Intelligent Transportation Systems, pp. 19–24 (2002)Google Scholar
  4. 4.
    Johansson, A.: Constant-net-time headway as a key mechanism behind pedestrian flow dynamics. Physical Review E 80, 26120–1 (2009)Google Scholar
  5. 5.
    Wu, S., Moore, B.E., Shah, M.: Chaotic invariants of lagrangian particle trajectories for anomaly detection in crowded scenes. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2054–2060 (2010)Google Scholar
  6. 6.
    Ge, W., Collins, R.: Marked point processes for crowd counting. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2913–2920 (2009)Google Scholar
  7. 7.
    Andrade, E.L., Scott, B., Fisher, R.B.: Hidden markov models for optical flow analysis in crowds. In: Proceedings of the International Conference on Pattern Recognition, pp. 460–463. IEEE Computer Society, Los Alamitos (2006)Google Scholar
  8. 8.
    Kratz, L., Nishino, K.: Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1446–1453 (2009)Google Scholar
  9. 9.
    Mehran, R., Oyama, A., Shah, M.: Abnormal crowd behavior detection using social force model. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 935–942 (2009)Google Scholar
  10. 10.
    Chan, A.B., Morrow, M., Vasconcelos, N.: Analysis of crowded scenes using holistic properties. In: Performance Evaluation of Tracking and Surveillance workshop at CVPR 2009, pp. 101–108 (2009)Google Scholar
  11. 11.
    Albiol, A., Silla, M., Albiol, A., Mossi, J.: Video analysis using corner motion statistics. In: Performance Evaluation of Tracking and Surveillance workshop at CVPR 2009, pp. 31–37 (2009)Google Scholar
  12. 12.
    Benabbas, Y., Ihaddadene, N., Djeraba, C.: Global analysis of motion vectors for event detection in crowd scenes. In: Performance Evaluation of Tracking and Surveillance Workshop at CVPR 2009, pp. 109–116 (2009)Google Scholar
  13. 13.
    Al-Hamadi, A., Michaelis, B.: An intelligent paradigm for multi-objects tracking in crowded environment. Journal of Digital Information Management 4, 183–190 (2006)Google Scholar
  14. 14.
    Wallach, H.M.: Conditional random fields: An introduction. Technical Report MS-CIS-04-21, University of Pennsylvania (2004)Google Scholar
  15. 15.
    Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: Proc. 18th International Conf. on Machine Learning, pp. 282–289 (2001)Google Scholar
  16. 16.
    Sha, F., Pereira, F.: Shallow parsing with conditional random fields (2003)Google Scholar
  17. 17.
    Ferryman, J., Shahrokni, A. (PETS (2009),
  18. 18.
    UMN: (Detection of unusual crowd activity),

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Saira Saleem Pathan
    • 1
  • Ayoub Al-Hamadi
    • 1
  • Bernd Michaelis
    • 1
  1. 1.Institute for Electronics, Signal Processing and Communications (IESK)Otto-von-Guericke-University MagdeburgGermany

Personalised recommendations