Real Time Tracking of Multiple Persons on Colour Image Sequences

  • Ghilès Mostafoui
  • Catherine Achard
  • Maurice Milgram
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3708)


We propose a real time algorithm to track moving persons without any a priori knowledge neither on the model of person, nor on their size or their number, which can evolve with time. It manages several problems such as occlusion and under or over-segmentations. The first step consisting in motion detection, leads to regions that have to be assigned to trajectories. This tracking step is achieved using a new concept: elementary tracks. They allow on the one hand to manage the tracking and on the other hand, to detect the output of occlusion by introducing coherent sets of regions. Those sets enable to define temporal kinematical model, shape model or colour model. Significant results have been obtained on several sequences with ground truth as shown in results.


Appearance Model Real Time Tracking Strong Edge Human Body Part Real Time Algorithm 
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.
    Achard, C., Mostafaoui, G., Milgram, M.: Object tracking based on kinematics with spatio-temporal blob. To appear in MVA 2005 (2005)Google Scholar
  2. 2.
    Bar-Shalom, Y., Li, X.R.: Multitarget-Mulisensor tracking. Yaakov Bar-Shalom (1995)Google Scholar
  3. 3.
    Comaniciu, D., Ramesh, V., Meer, P.: Real-time tracking of non-rigid objects using mean shift. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition using silhouettes, International Conference on Pattern Recognition, June 2000, pp. 77–82 (1998)Google Scholar
  4. 4.
    Denoulet, J., Mostafaoui, G., Lacassagne, L., Merigot, A.: Robust Embedded Hardware implementation of Motion Markov Detection and hysteresis thresholding in colors sequences, pp. 142–151 (to appear)Google Scholar
  5. 5.
    Haritaoglu, I., Harwood, D., Davis, L.S.: Ghost: A human body part labelling system. In: CAMP 2005 (2005)Google Scholar
  6. 6.
    Haritaoglu, I., Harwood, D., Davis, L.S.: W4S: a real time system for detecting and tracking people in 2,5D. In: European Conference Computer Vision, Maryland, pp. 877–892 (1998)Google Scholar
  7. 7.
    Hue, C., Le, J.P.: cadre, P. Perez, Tracking multiple objects with particle filtering, RR INRIA no 4033 (2000)Google Scholar
  8. 8.
    Isard, M., Blake, A.: Condensation conditional density propagation for visual tracking. Int. J. Computer Vision 29(1), 5–28 (1998)CrossRefGoogle Scholar
  9. 9.
    Moon, H., Chellappa, R., Rosenfeld, A.: Tracking of Human Activities Using Shape-encoded Particle Propagation. In: ICIP 2001, vol. 1, pp. 357–360 (2001)Google Scholar
  10. 10.
    Mittal, A., Davis, L.S.: M2 Tracker: A Multi-View Approach to Segmenting and tracking people in a Cluttered Scene. IJCV(51) (3), 189–203 (2003)Google Scholar
  11. 11.
    Park, S., Aggarwal, J.K.: Segmentation and tracking of interacting human body parts under occlusion and shadowing. In: Motion 2002, pp. 105–111 (2002)Google Scholar
  12. 12.
    Reid, D.B.: An algorithm for Tracking Multiple Targets. IEEE Trans. on Automatic Control AC-24(6), 843–854 (1979)CrossRefGoogle Scholar
  13. 13.
    Senior, A.: Tracking People with Probabilistic Appearance Models. In: Pets 2002, pp. 48–55 (2002)Google Scholar
  14. 14.
    Wang, L., Ning, H., Tan, T., Hu, W.: Fusion of static and dynamic body biometrics for gait recognition. In: ICCV 2003 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Ghilès Mostafoui
    • 1
  • Catherine Achard
    • 1
  • Maurice Milgram
    • 1
  1. 1.LISIFParis

Personalised recommendations