Characterization of Dense Crowd Using Gibbs Entropy

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 704)


Automatic understanding of crowd dynamics through computer vision is a challenging task. There exists a number of works related to crowd behaviors, especially when the gatherings are large. A crowd can be characterized by its speed, randomness, or density. Large gatherings at sociocultural events often cause traffic congestion at cities or even they lead to untoward incidents such as stampede or accidents. However, if the crowd dynamics can be understood or predicted, precautionary measures can be taken by the administrative authority. In this paper, a Gibbs entropy-based crowd characterization has been proposed to estimate crowd dynamics, especially at large gatherings. The average frame energy estimated by the kinetic energy of moving particles has been used to estimate the speed of movement, while the average frame entropy gives information about the randomness in the crowd. The proposed method has been evaluated on two publicly available datasets as well as our dataset videos recorded during sociocultural gatherings. It has been observed that the proposed entropy-energy-based analysis can successfully characterize crowd dynamics and it can be used for flow analysis and density estimation.


Crowd dynamics Crowd characterization Gibbs entropy Crowd flow analysis 



This research work is funded by Science and Engineering Research Board (SERB), Department of Science and Technology, Government of India, through the grant YSS/2014/000046.


  1. 1.
    Ratha Yatra (puri)—wikipedia., (Accessed on 07/05/2017)
  2. 2.
    Ali, S., Shah, M.: A lagrangian particle dynamics approach for crowd flow segmentation and stability analysis pp. 1–6 (2007)Google Scholar
  3. 3.
    Cao, L., Zhang, X., Ren, W., Huang, K.: Large scale crowd analysis based on convolutional neural network. Pattern Recognition 48(10), 3016–3024 (2015)Google Scholar
  4. 4.
    Chaker, R., Al Aghbari, Z., Junejo, I.N.: Social network model for crowd anomaly detection and localization. Pattern Recognition 61, 266–281 (2017)Google Scholar
  5. 5.
    Farnebäck, G.: Two-frame motion estimation based on polynomial expansion. Image analysis pp. 363–370 (2003)Google Scholar
  6. 6.
    Foroughi, H., Ray, N., Zhang, H.: Robust people counting using sparse representation and random projection. Pattern Recognition 48(10), 3038–3052 (2015)Google Scholar
  7. 7.
    Jaynes, E.T.: Gibbs vs boltzmann entropies. American Journal of Physics 33(5), 391–398 (1965)Google Scholar
  8. 8.
    Junior, J.C.S.J., Musse, S.R., Jung, C.R.: Crowd analysis using computer vision techniques. IEEE Signal Processing Magazine 27(5), 66–77 (2010)Google Scholar
  9. 9.
    Kataoka, H., Hashimoto, K., Iwata, K., Satoh, Y., Navab, N., Ilic, S., Aoki, Y.: Extended co-occurrence hog with dense trajectories for fine-grained activity recognition pp. 336–349 (2014)Google Scholar
  10. 10.
    Liang, R., Zhu, Y., Wang, H.: Counting crowd flow based on feature points. Neurocomputing 133, 377–384 (2014)Google Scholar
  11. 11.
    Mancas, M., Riche, N., Leroy, J., Gosselin, B.: Abnormal motion selection in crowds using bottom-up saliency pp. 229–232 (2011)Google Scholar
  12. 12.
    Mehran, R., Moore, B., Shah, M.: A streakline representation of flow in crowded scenes. Computer Vision–ECCV 2010 pp. 439–452 (2010)Google Scholar
  13. 13.
    Mota, V.F., Perez, E.d.A., Maciel, L.M., Vieira, M.B., Gosselin, P.H.: A tensor motion descriptor based on histograms of gradients and optical flow. Pattern Recognition Letters 39, 85–91 (2014)Google Scholar
  14. 14.
    Rodriguez, M., Laptev, I., Sivic, J., Audibert, J.Y.: Density-aware person detection and tracking in crowds pp. 2423–2430 (2011)Google Scholar
  15. 15.
    Santoro, F., Pedro, S., Tan, Z.H., Moeslund, T.B.: Crowd analysis by using optical flow and density based clustering pp. 269–273 (2010)Google Scholar
  16. 16.
    Solmaz, B., Moore, B.E., Shah, M.: Identifying behaviors in crowd scenes using stability analysis for dynamical systems. IEEE Transactions on Pattern Analysis and Machine Intelligence 34(10), 2064–2070 (2012)Google Scholar
  17. 17.
    Wang, T., Snoussi, H.: Detection of abnormal events via optical flow feature analysis. Sensors 15(4), 7156–7171 (2015)Google Scholar
  18. 18.
    Wu, S., Su, H., Yang, H., Zheng, S., Fan, Y., Zhou, Q.: Bilinear dynamics for crowd video analysis. Journal of Visual Communication and Image Representation (2017)Google Scholar
  19. 19.
    Wu, S., San Wong, H.: Crowd motion partitioning in a scattered motion field. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 42(5), 1443–1454 (2012)Google Scholar
  20. 20.
    Yapa, R.D., Harada, K.: Connected component labeling algorithms for gray-scale images and evaluation of performance using digital mammograms. International Journal of Computer Science and Network Security 8(6), 33–41 (2008)Google Scholar
  21. 21.
    Zhan, B., Monekosso, D.N., Remagnino, P., Velastin, S.A., Xu, L.Q.: Crowd analysis: a survey. Machine Vision and Applications 19(5), 345–357 (2008)Google Scholar
  22. 22.
    Zhong, Z., Ye, W., Wang, S., Yang, M., Xu, Y.: Crowd energy and feature analysis pp. 144–150 (2007)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.IIT BhubaneswarBhubaneswarIndia
  2. 2.IIT RoorkeeRoorkeeIndia

Personalised recommendations