Motion Estimation with Edge Continuity Constraint for Crowd Scene Analysis

  • B. Zhan
  • P. Remagnino
  • S. A. Velastin
  • N. Monekosso
  • L. -Q. Xu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4292)


This paper presents a new motion estimation method aimed at crowd scene analysis in complex video sequences. The proposed technique makes use of image descriptors extracted from points lying at the maximum curvature on the Canny edge map of an analyzed image. Matches between two consecutive frames are then carried out by searching for descriptors that satisfy both a well-defined similarity metric and a structural constraint imposed by the edge map. A preliminary assessment using real-life video sequences gives both qualitative and quantitative results.


Video Sequence Motion Estimation Corner Point Interest Point Edge Information 
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.
    Helbing, D., Molnar, P.: Social force model for pedestrian dynamics. Physical Review 51, 4282–4286 (1995)Google Scholar
  2. 2.
    Pan, X., Han, C.S., Law, K.H.: Human and social behavior in computational modeling and analysis of egress. Building Future Council Doctoral Program (2005)Google Scholar
  3. 3.
    Le Bon, G.: The Crowd. Cherokee Publishing Company (1895)Google Scholar
  4. 4.
    Marana, A., Velastin, S., Costa, L.d.F., Lotufo, R.: Automatic estimation of crowd density using texture. Safety Science 28, 165–175 (1988)CrossRefGoogle Scholar
  5. 5.
    Ma, R., Li, L., Huang, W., Tian, Q.: On pixel count based crowd density estimation for visual surveillance. In: IEEE Conference on Cybernetics and Intelligent Systems, pp. 170–173. IEEE, Los Alamitos (2004)Google Scholar
  6. 6.
    Mathes, T., Piater, J.: Robust non-rigid object tracking using point distribution models. In: British Machine Vision Conference, Oxford (2005)Google Scholar
  7. 7.
    Venegas, S., Knebel, S., Thiran, J.P.: Multi-object tracking using particle filter algorithm on the top-view plan (2003)Google Scholar
  8. 8.
    Smith, K., Gatica-Perez, D., Odobez, J.: Using Particles to Track Varying Numbers of Interacting People. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 1 (2005)Google Scholar
  9. 9.
    Marques, J., Jorge, P., Abrantes, A., Lemos, J.: Tracking Groups of Pedestrians in Video Sequences. IEEE WoMOT 9, 101 (2003)Google Scholar
  10. 10.
    Zhan, B., Remagnino, P., Velastin, S.: Mining paths of complex crowd scenes. LNCS, pp. 126–133. Springer, Heidelberg (2005)Google Scholar
  11. 11.
    Andrade, E., Blunsden, S., Fisher, B.: Hidden markov models for optical flow analysis in crowds. In: The 18th international conference on pattern recognition (2006)Google Scholar
  12. 12.
    Cohen, I., Ayache, N., Sulger, P.: Tracking points on deformable objects using curvature information. In: Proceedings of the Second European Conference on Computer Vision, pp. 458–466 (1992)Google Scholar
  13. 13.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: Alvey Vision Conference, pp. 147–151 (1988)Google Scholar
  14. 14.
    Mokhtarian, F., Mackworth, A.K.: A theory of multiscale, curvature-based shape representation for planar curves. IEEE Trans. Pattern Anal. Mach. Intell. 14, 789–805 (1992)CrossRefGoogle Scholar
  15. 15.
    Young, I., Van Vliet, L.: Recursive implementation of the Gaussian filter. Signal processing 44, 139–151 (1995)CrossRefGoogle Scholar
  16. 16.
    Stauffer, C., Grimson, W.: Adaptive background mixture models for real-time tracking. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 246–252 (1999)Google Scholar
  17. 17.
    EC: Funded caviar project (2002-2005),

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • B. Zhan
    • 1
  • P. Remagnino
    • 1
  • S. A. Velastin
    • 1
  • N. Monekosso
    • 1
  • L. -Q. Xu
    • 2
  1. 1.Digital Imaging Research CentreKingston UniversityUK
  2. 2.British Telecom ResearchIpswichUK

Personalised recommendations