Crowd Detection with a Multiview Sampler

  • Weina Ge
  • Robert T. Collins
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6315)


We present a Bayesian approach for simultaneously estimating the number of people in a crowd and their spatial locations by sampling from a posterior distribution over crowd configurations. Although this framework can be naturally extended from single to multiview detection, we show that the naive extension leads to an inefficient sampler that is easily trapped in local modes. We therefore develop a set of novel proposals that leverage multiview geometry to propose global moves that jump more efficiently between modes of the posterior distribution. We also develop a statistical model of crowd configurations that can handle dependencies among people and while not requiring discretization of their spatial locations. We quantitatively evaluate our algorithm on a publicly available benchmark dataset with different crowd densities and environmental conditions, and show that our approach outperforms other state-of-the-art methods for detecting and counting people in crowds.


Camera View Foreground Pixel Pedestrian Detection Crowd Density Angular Extent 
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.


  1. 1.
    Fleuret, F., Lengagne, R., Fua, P.: Fixed point probability field for complex occlusion handling. In: ICCV (2005)Google Scholar
  2. 2.
    Zhao, T., Nevatia, R.: Bayesian human segmentation in crowded situations. In: CVPR (2003)Google Scholar
  3. 3.
    Ge, W., Collins, R.T.: Marked point processes for crowd counting. In: CVPR (2009)Google Scholar
  4. 4.
    Leibe, B., Seemann, E., Schiele, B.: Pedestrian detection in crowded scenes. In: CVPR, pp. 878–885 (2005)Google Scholar
  5. 5.
    Bolme, D.S., Draper, B.A., Beveridge, J.R.: Average of synthetic exact filters. In: CVPR, pp. 2105–2112 (2009)Google Scholar
  6. 6.
    Tu, P., Sebastian, T., Doretto, G., Krahnstoever, N., Rittscher, J., Yu, T.: Unified crowd segmentation. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 691–704. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  7. 7.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: ICCV (2005)Google Scholar
  8. 8.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: CVPR, pp. 511–518 (2001)Google Scholar
  9. 9.
    Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: CVPR (2008)Google Scholar
  10. 10.
    Ge, W., Collins, R.T.: Evaluation of sampling-based pedestrian detection for crowd counting. In: Winter-PETS (2009)Google Scholar
  11. 11.
    Ortner, M., Descombes, X., Zerubia, J.: A marked point process of rectangles and segments for automatic analysis of digital elevation models. TPAMI 30, 105–119 (2008)Google Scholar
  12. 12.
    Rue, H., Hurn, M.: Bayesian object identification. Biometrika 86, 649–660 (1999)zbMATHCrossRefMathSciNetGoogle Scholar
  13. 13.
    Mittal, A., Davis, L.S.: M2Tracker: A multi-view approach to segmenting and tracking people in a cluttered scene using region-based stereo. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 18–33. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  14. 14.
    Khan, S.M., Shah, M.: Tracking multiple occluding people by localizing on multiple scene planes. TPAMI 31, 505–519 (2009)Google Scholar
  15. 15.
    Tyagi, A., Keck, M., Davis, J., Potamianos, G.: Kernel-Based 3D tracking. In: IEEE International Workshop on Visual Surveillance (2007)Google Scholar
  16. 16.
    Otsuka, K., Mukawa, N.: Multiview occlusion analysis for tracking densely populated objects based on 2-D visual angles. In: CVPR, vol. 1, pp. 90–97 (2004)Google Scholar
  17. 17.
    Yang, D.B., González-Baños, H.H., Guibas, L.J.: Counting people in crowds with a real-time network of simple image sensors. In: ICCV, pp. 122–129 (2003)Google Scholar
  18. 18.
    Alahi, A., Jacques, L., Boursier, Y., Vandergheynst, P.: Sparsity-driven people localization algorithm: Evaluation in crowded scenes environments. In: Winter-PETS (2009)Google Scholar
  19. 19.
    Dellaert, F., Seitz, S., Thorpe, C., Thrun, S.: EM, MCMC, and chain flipping for structure from motion with unknown correspondence. Machine Learning 50 (2003)Google Scholar
  20. 20.
    Andricioaei, I., Straub, J.E., Voter, A.F.: Smart darting Monte Carlo. The Journal of Chemical Physics 114, 6994–7000 (2001)CrossRefGoogle Scholar
  21. 21.
    Sminchisescu, C., Welling, M., Hinton, G.: A Mode-Hopping MCMC Sampler. Technical Report CSRG-478, University of Toronto (2003)Google Scholar
  22. 22.
    Zhu, S., Zhang, R., Tu, Z.: Integrating bottom-up/top-down for object recognition by data driven Markov Chain Monte Carlo. In: CVPR, pp. 738–745 (2000)Google Scholar
  23. 23.
    van Lieshout, M.: Markov Point Processes and their Applications. Imperial College Press, London (2000)zbMATHCrossRefGoogle Scholar
  24. 24.
    Berclaz, J., Fleuret, F., Fua, P.: Multiple object tracking using flow linear programming. In: Winter-PETS (2009)Google Scholar
  25. 25.
    Green, P.: Reversible jump Markov chain Monte-Carlo computation and Bayesian model determination. Biometrika 82, 711–732 (1995)zbMATHCrossRefMathSciNetGoogle Scholar
  26. 26.
    Ellis, A., Shahrokni, A., Ferryman, J.M.: PETS 2009 and Winter-PETS 2009 results: A combined evaluation. In: Winter-PETS (2009)Google Scholar
  27. 27.
    Zivkovic, Z.: Improved adaptive gaussian mixture model for background subtraction. In: ICPR, vol. 2, pp. 28–31 (2004)Google Scholar
  28. 28.
    Chan, A., Morrow, M., Vasconcelos, N.: Analysis of crowded scenes using holistic properties. In: PETS (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Weina Ge
    • 1
  • Robert T. Collins
    • 1
  1. 1.The Pennsylvania State UniversityUniversity ParkUSA

Personalised recommendations