A Streakline Representation of Flow in Crowded Scenes

  • Ramin Mehran
  • Brian E. Moore
  • Mubarak Shah
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6313)


Based on the Lagrangian framework for fluid dynamics, a streakline representation of flow is presented to solve computer vision problems involving crowd and traffic flow. Streaklines are traced in a fluid flow by injecting color material, such as smoke or dye, which is transported with the flow and used for visualization. In the context of computer vision, streaklines may be used in a similar way to transport information about a scene, and they are obtained by repeatedly initializing a fixed grid of particles at each frame, then moving both current and past particles using optical flow. Streaklines are the locus of points that connect particles which originated from the same initial position. In this paper, a streakline technique is developed to compute several important aspects of a scene, such as flow and potential functions using the Helmholtz decomposition theorem. This leads to a representation of the flow that more accurately recognizes spatial and temporal changes in the scene, compared with other commonly used flow representations. Applications of the technique to segmentation and behavior analysis provide comparison to previously employed techniques, showing that the streakline method outperforms the state-of-the-art in segmentation, and opening a new domain of application for crowd analysis based on potentials.


Support Vector Machine Divergent Region Social Force Model Crowded Scene Crowd Motion 
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.
    Ali, S., Shah, M.: A lagrangian particle dynamics approach for crowd flow segmentation and stability analysis. In: CVPR (2007)Google Scholar
  2. 2.
    Mehran, R., Oyama, A., Shah, M.: Abnormal behavior detection using social force model. In: CVPR (2009)Google Scholar
  3. 3.
    Wijk, V., Jarke, J.: Image based flow visualization. In: SIGGRAPH (2002)Google Scholar
  4. 4.
    Helman, J., Hesselink, L.: Visualizing vector field topology in fluid flows. IEEE Comput. Graph. Appl. 11, 36–46 (1991)CrossRefGoogle Scholar
  5. 5.
    Landau, L., Lifshitz, E.: Advanced Mechanics of Fluids (1959)Google Scholar
  6. 6.
    Johnson, N., Hogg, D.: Learning the distribution of object trajectories for event recognition (1995)Google Scholar
  7. 7.
    Marques, J.S., Jorge, P.M., Abrantes, A.J., Lemos, J.M.: Tracking groups of pedestrians in video sequences. In: Proc. CVPRW (2003)Google Scholar
  8. 8.
    Pellegrini, S., Ess, A., Schindler, K., van Gool, L.: You’ll never walk alone: Modeling social behavior for multi-target tracking. In: ICCV (2009)Google Scholar
  9. 9.
    Brostow, G., Cipolla, R.: Unsupervised bayesian detection of independent motion in crowds. In: CVPR (2006)Google Scholar
  10. 10.
    Garate, C., Bilinsky, P., Bremond, P.B.: Crowd event recognition using hog tracker (2009)Google Scholar
  11. 11.
    Ke, Y., Sukthankar, R., Hebert, M.: Event detection in crowded videos. In: ICCV (2007)Google Scholar
  12. 12.
    Seemann, E., Fritz, M., Schiele, B.: Towards robust pedestrian detection in crowded image sequences. In: CVPR (2007)Google Scholar
  13. 13.
    Ali, S., Shah, M.: Floor fields for tracking in high density crowd scenes. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 1–14. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  14. 14.
    Saleemi, I., Hartung, L., Shah, M.: Scene understanding by statistical modeling of motion patterns. In: CVPR (2010)Google Scholar
  15. 15.
    Kratz, L., Nishino, K.: Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models. In: CVPR (2009)Google Scholar
  16. 16.
    Andrade, E.L., Blunsden, S., Fisher, R.B.: Modelling crowd scenes for event detection. In: ICPR (2006)Google Scholar
  17. 17.
    Sand, P., Teller, S.: Particle video: Long-range motion estimation using point trajectories. In: CVPR (2006)Google Scholar
  18. 18.
    Courty, N., Corpetti, T.: Crowd motion capture. Comput. Animat. Virtual Worlds 18, 361–370 (2007)CrossRefGoogle Scholar
  19. 19.
    Hughes, R.: The flow of human crowds. Annual Review of Fluid Mechanics 35, 169–182 (2003)CrossRefGoogle Scholar
  20. 20.
    Hama, F.R.: Streaklines in a perturbed shear flow. Phys. Fluids 5, 644–650 (1962)zbMATHCrossRefGoogle Scholar
  21. 21.
    Helbing, D., Molnar, P.: Social force model for pedestrian dynamics. Physical Review E 51 (1995)Google Scholar
  22. 22.
    Corpetti, T., Memin, E., Perez, P.: Extraction of singular points from dense motion fields: An analytic approach. Journal of Mathematical Imaging and Vision (2003)Google Scholar
  23. 23.
    University of Minnesota - Crowd Activity Dataset,

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Ramin Mehran
    • 1
  • Brian E. Moore
    • 2
  • Mubarak Shah
    • 1
  1. 1.Computer Vision Lab 
  2. 2.Department of MathematicsUniversity of Central Florida 

Personalised recommendations