Real-time pedestrian tracking in natural scenes

  • J. Denzler
  • H. Niemann
Object Recognition and Tracking
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1296)


In computer vision real-time tracking of moving objects in natural scenes has become more and more important. In this paper we describe a complete system for data driven tracking of moving objects. We apply the system to tracking pedestrians in natural scenes. No specialized hardware is used. To achieve the necessary efficiency several principles of active vision, namely selection in space, time, and resolution are implemented. For object tracking, a contour based approach is used which allows contour extraction and tracking within the image frame rate on general purpose architectures. A pan/tilt camera is steered by a camera control module to pursue the moving object. A dedicated attention module is responsible for the robustness of the complete system. The experiments over several hours prove the robustness and accuracy of the whole system. Tracking of pedestrians in a natural scene has been successful in 79% of the time.


Active Contour Object Tracking Natural Scene Active Vision Specialized Hardware 
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.
    M. Armstrong and A. Zisserman. Robust object tracking. In Second Asian Conference on Computer Vision, pages 1/584-I/62, Singapore, 1995.Google Scholar
  2. 2.
    R. Curwen and A. Blake. Dynamic contours: Real-time active splines. In A. Blake and A. Yuille, editors, Active Vision, pages 39–58. MIT Press, Cambridge, Massachusetts, London, England, 1992.Google Scholar
  3. 3.
    K. Daniilidis, M. Hansen, C. Krauss, and G. Sommer. Auf dem Weg zum künstlichen aktiven Sehen: Modellfreie Bewegungsverfolgung durch Kameranachführung. In DAGM 1995, Bielefeld, pages 277–284, 1995.Google Scholar
  4. 4.
    J. Denzler. Active Vision for Real-Time Object Tracking. Dissertation, Technische Fakultät, Universität Erlangen-Nürnberg, Erlangen, in preparation, 1997.Google Scholar
  5. 5.
    J. Denzler and H. Niemann. Echtzeitobjektverfolgung mit aktiven Strahlen. In Mustererkennung, 1996, pages 84–91, Heidelberg, 1996.Google Scholar
  6. 6.
    G.D. Hager and K. Toyama. X vision: Combining image warping and geometric constraints for fast visual tracking. In A. Blake, editor, Computer Vision — ECCV 96, pages 507–517, Berlin, Heidelberg, New York, London, 1996. Lecture Notes in Computer Science.Google Scholar
  7. 7.
    M. Kass, A. Wittkin, and D. Terzopoulos. Snakes: Active contour models. International Journal of Computer Vision, 2(3):321–331, 1988.CrossRefGoogle Scholar
  8. 8.
    D. Murray and A. Basu. Motion tracking with an active camera. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16(5):449–459, 1994.CrossRefGoogle Scholar
  9. 9.
    S.M. Smith and J.M. Brady. Asset-2: Real-time motion segmentation and shape tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 17(8):814–820, 1995.CrossRefGoogle Scholar
  10. 10.
    F. Thomanek and E.D. Dickmanns. Autonomous road vehicle guidance in normal traffic. In Second Asian Conference on Computer Vision, pages III/11–III/15, Singapore, 1995.Google Scholar
  11. 11.
    T. Uhlin, P Nordlund, A. Maki, and J.O. Eklundh. Towards an active visual observer. In International Conference on Computer Vision, pages 679–686, Cambridge, Massachusetts, 1995.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • J. Denzler
    • 1
  • H. Niemann
    • 1
  1. 1.Lehrstuhl für Mustererkennung (Informatik 5)Universität Erlangen-NürnbergErlangen

Personalised recommendations