Tracking Pedestrians Under Occlusion Using Multiple Cameras

  • Jorge P. Batista
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3212)


This paper presents a integrated solution to track multiple non-rigid objects (pedestrians) in a multiple cameras system with ground-plane trajectory prediction and occlusion modelling. The resulting system is able to maintain the tracking of pedestrians before, during and after occlusion. Pedestrians are detected and segmented using a dynamic background model combined with motion detection and brightness and color distortion analysis. Two levels of tracking have been implemented: the image level tracking and the ground-plane level tracking. Several target cues are used to disambiguate between possible candidates of correspondence in the tracking process: spacial and temporal estimation, color and object height. A simple and robust solution for image occlusion monitoring and grouping management is described. Experiments in tracking multiple pedestrians in a dual camera setup with common field of view are presented.


Sensor Node Multiple Camera Foreground Pixel Object Descriptor Shadow Detection 
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.
    Collins, R., et al.: A System for Video Surveillance and Monitoring. CMU-RI-TR- 00-12, Carnegie Mellon University (2000)Google Scholar
  2. 2.
    Bar-Shalom, Y., Fortmann, T.: Tracking and Data Association. Academic Press Inc., New-York (1988)zbMATHGoogle Scholar
  3. 3.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2000)zbMATHGoogle Scholar
  4. 4.
    Horpraset, T., Harwood, D., Davis, L.: A statistical approach for real-time robust background subtraction and shadow detection. In: ICCV 1999 Frame Rate Workshop (1999)Google Scholar
  5. 5.
    Haritaoglu, I., Harwood, D., Davis, L.: Hidra-Multiple people detection and tracking using silhouettes. In: IEEE Workshop on Visual Surveillance (1996)Google Scholar
  6. 6.
    Pieter, J., Crowley, J.: Multi-Modal Tracking of Interacting targets using Gaussian Approximations. In: PETS 2000 (2000)Google Scholar
  7. 7.
    Swain, J., Ballard, D.: Color Indexing. IJCV 7(1), 11–32 (1991)CrossRefGoogle Scholar
  8. 8.
    McKenna, S., Raja, Y., Gong, S.: Tracking Colour Objects using Adaptive Mixture Models. Image and Vision Computing 17, 225–231 (1999)CrossRefGoogle Scholar
  9. 9.
    Black, J., Ellis, T.: Multi Camera Image Tracking. In: IEEE PETS 2001(2001)Google Scholar
  10. 10.
    Qai, Q., Aggarwal, K.: Automatic Tracking of Human Motion in Indoor Scenes Across Multiple Synchronized Video Streams. In: ICCC 1998, Bombay (1998)Google Scholar
  11. 11.
    Zhao, T., Nevatia, R., Lv, F.: Segmentation and Tracking of Multiple Humans in Complex Situations. In: IEEE CVPR, Hawaii (2001)Google Scholar
  12. 12.
    McKenna, S., Jabri, S., Duric, Z., Rosenfeld, A.: Tracking Groups of People. CVIU 80, 42–56 (2000)zbMATHGoogle Scholar
  13. 13.
    Mittal, A.: Video Analysis Under Severe Occusions, PhD Thesis, University of Maryland (2002)Google Scholar
  14. 14.
    Yang, D., González-Baños, H., Guibas, L.: Counting People in Crowds with a Real- Time Network of Simple Image Sensors. In: IEEE ICCV 2003 (2003)Google Scholar
  15. 15.
    Remagnino, P., Jones, G.A.: Automated Registration of Surveillance Data for Multi-Camera Fusion. In: ISIF, pp. 1190–1197 (2002)Google Scholar
  16. 16.
    Chang, T., Gong, S.: Bayesian Modality Fusion for Tracking Multiple People with a Multi-Camera System. In: Proc. European Workshop on Advanced Video-based Surveillance Systems, UK (2001)Google Scholar
  17. 17.
    Khan, S., Javed, O., Rasheed, Z., Shah, M.: Human Tracking in Multiple Cameras. In: IEEE ICCV 2001, pp. 331–336 (2001)Google Scholar
  18. 18.
    Kang, J., Cohen, I., Medioni, G.: Continuous Tracking Within and Across Camera Streams. In: IEEE CVPR 2003, pp. 267–272 (2003)Google Scholar
  19. 19.
    Kang, J., Cohen, I., Medioni, G.: Continuous Multi-Views Tracking using Tensor Voting. In: Workshop on Motion and Video Computing (MOTION 2002), pp. 181–186 (2002)Google Scholar
  20. 20.
    Stein, G.: Tracking from Multiple View Points: Self-calibration of Space and Time. Image Understanding Workshop (November 1998) Google Scholar
  21. 21.
    Brémond, F., Thonnat, M.: Tracking Multiple Non-Rigid Objects in Video Sequences. IEEE Transaction on Circuits and Systems for Video Technology Journal 8(5) (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Jorge P. Batista
    • 1
  1. 1.ISR-Institute of Systems and Robotics, DEEC/FCTUniversity of CoimbraCoimbraPortugal

Personalised recommendations