Advertisement

Statistically Representative Cloud of Particles for Crowd Flow Tracking

  • Patrick Jamet
  • Stephen Chai Kheh Chew
  • Antoine Fagette
  • Jean-Yves Dufour
  • Daniel Racoceanu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9443)

Abstract

This paper deal with the flow tracking topic applied to dense crowds of pedestrians. Using the estimated density, a cloud of particles is spread on the image and propagated according to the optical flow. Each particles embedding physical properties similar to those of a pedestrian, this cloud of particles is considered as statistically representative of the crowd. Therefore, the behavior of the particles can be validated with respect to the behavior expected from pedestrians and potentially optimized if needed. Three applications are derived by analysis of the cloud behavior: the detection of the entry and exit areas of the crowd in the image, the detection of dynamic occlusions and the possibility to link entry areas with exit ones according to the flow of the pedestrians. The validation is performed on synthetic data and shows promising results.

Keywords

Particle video Crowd Flow tracking Entry-exit areas detection Occlusions Entry-exit areas linkage 

References

  1. 1.
    Yilmaz, A., Javed, O., Shah, M.: Object tracking: A survey. Acm Comput. Surv. (CSUR) 38, 1–45 (2006). Article 13CrossRefGoogle Scholar
  2. 2.
    Zhou, H., Yuan, Y., Shi, C.: Object tracking using sift features and mean shift. Comput. Vis. Image Underst. 113, 345–352 (2009)CrossRefGoogle Scholar
  3. 3.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2001, Vol. 1, p. I-511. IEEE (2001)Google Scholar
  4. 4.
    Isard, M., Blake, A.: Condensation - conditional density propagation for visual tracking. Int. J. Comput. Vision 29, 5–28 (1998)CrossRefGoogle Scholar
  5. 5.
    Chau, D.P., Bremond, F., Thonnat, M.: Object tracking in videos: Approaches and issues. arXiv preprint arXiv:1304.5212 (2013)
  6. 6.
    Corpetti, T., Heitz, D., Arroyo, G., Memin, E., Santa-Cruz, A.: Fluid experimental flow estimation based on an optical-flow scheme. Exp. Fluids 40, 80–97 (2006)CrossRefGoogle Scholar
  7. 7.
    Liu, T., Shen, L.: Fluid flow and optical flow. J. Fluid Mech. 614, 1 (2008)MathSciNetCrossRefzbMATHGoogle Scholar
  8. 8.
    Andrade, E.L., Blunsden, S., Fisher, R.B.: Modelling crowd scenes for event detection. In: Proceedings of the 18th International Conference on Pattern Recognition ICPR 2006, vol. 1, pp. 175–178 (2006)Google Scholar
  9. 9.
    Sand, P., Teller, S.: Particle video: Long-range motion estimation using point trajectories. In: Computer Vision and Pattern Recognition, vol. 2, pp. 2195–2202 (2006)Google Scholar
  10. 10.
    Ali, S., Shah, M.: A lagrangian particle dynamics approach for crowd flow segmentation and stability analysis. In: IEEE International Conference on Computer Vision and Pattern Recognition (2007)Google Scholar
  11. 11.
    Mehran, R., Morre, B.E., Shah, M.: A streakline representation of flow in crowded scenes. In: Proceedings of the 11th European Conference on Computer Vision (2010)Google Scholar
  12. 12.
    Helbing, D., Molnár, P.: Social force model for pedestrian dynamics. Phys. Rev. E 51, 4282 (1995)CrossRefGoogle Scholar
  13. 13.
    Mehran, R., Omaya, A., Shah, M.: Abnormal crowd behavior detection using social force model. In: Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (2009)Google Scholar
  14. 14.
    Rodriguez, M., Sivic, J., Laptev, I.: Analysis of crowded scenes in video. In: Intelligent Video Surveillance Systems, vol. 1, pp. 251–272 (2012)Google Scholar
  15. 15.
    Farnebäck, G.: Two-frame motion estimation based on polynomial expansion. In: Gustavsson, T., Bigun, J. (eds.) SCIA 2003. LNCS, vol. 2749, pp. 363–370. Springer, Heidelberg (2003) CrossRefGoogle Scholar
  16. 16.
    Tan, D., Chen, Z.: On a general formula of fourth order runge-kutta method. J. Math. Sci. Math. Educ. 7(2), 1–10 (2012)Google Scholar
  17. 17.
    Allain, P., Courty, N., Corpetti, T.: AGORASET: a dataset for crowd video analysis. In: 1st ICPR International Workshop on Pattern Recognition and Crowd Analysis, Tsukuba, Japan (2012)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Patrick Jamet
    • 1
    • 3
  • Stephen Chai Kheh Chew
    • 1
  • Antoine Fagette
    • 1
    • 3
  • Jean-Yves Dufour
    • 2
  • Daniel Racoceanu
    • 3
  1. 1.Thales Solutions Asia Pte LtdSingaporeSingapore
  2. 2.ThereSIS - Vision LabThales Services - Campus PolytechniquePalaiseauFrance
  3. 3.CNRS IPAL UMI 2955 Joint LabSingaporeSingapore

Personalised recommendations