Articulated-Body Tracking Through Anisotropic Edge Detection

  • David Knossow
  • Joost van de Weijer
  • Radu Horaud
  • Rémi Ronfard
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4358)


This paper addresses the problem of articulated motion tracking from image sequences. We describe a method that relies on both an explicit parameterization of the extremal contours and on the prediction of the human boundary edges in the image. We combine extremal contour prediction and edge detection in a non linear minimization process. The error function that measures the discrepancy between observed image edges and predicted model contours is minimized using an analytical expression of the Jacobian that maps joint velocities onto extremal contour velocities. In practice, we model people both by their geometry (truncated elliptic cones) and their articulated structure – a kinematic model with 40 rotational degrees of freedom. To overcome the flaws of standard edge detection, we introduce a model-based anisotropic Gaussian filter. The parameters of the anisotropic Gaussian are automatically derived from the kinematic model through the prediction of the extremal contours. The theory is validated by performing full body motion capture from six synchronized video sequences at 30 fps without markers.


Edge Detection Kinematic Model Image Patch Kinematic Chain Rigid 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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Agarwal, A., Triggs, B.: Learning to track 3d human motion from silhouettes. In: International Conference on Machine Learning, Banff, July 2004, pp. 9–16 (2004),
  2. 2.
    Deutscher, J., Blake, A., Reid, I.: Articulated body motion capture by annealed particle filtering. In: Computer Vision and Pattern Recognition, pp. 2126–2133 (2000)Google Scholar
  3. 3.
    Lan, X., Huttenlocher, D.P.: A unified spatio-temporal articulated model for tracking. In: Computer Vision and Pattern Recognition, pp. 722–729 (2004)Google Scholar
  4. 4.
    Bregler, C., Malik, J., Pullen, K.: Twist based acquisition and tracking of animal and human kinematics. International Journal of Computer Vision 56(3), 179–194 (2004)CrossRefGoogle Scholar
  5. 5.
    Sminchisescu, C., Triggs, B.: Estimating articulated human motion with covariance scaled sampling. International Journal of Robotics Research 22(6), 371–379 (2003)CrossRefGoogle Scholar
  6. 6.
    Delamarre, Q., Faugeras, O.: 3d articulated models and multi-view tracking with physical forces. Computer Vision and Image Understanding 81, 328–357 (2001)zbMATHCrossRefGoogle Scholar
  7. 7.
    Gavrila, D.M., Davis, L.S.: 3d model-based tracking of humans in action: a multi-view approach. In: Conference on Computer Vision and Pattern Recognition, San Francisco, CA, pp. 73–80 (1996)Google Scholar
  8. 8.
    Ilic, S., Salzmann, M., Fua, P.: Implicit surfaces make for better silhouettes. In: European Conference on Computer Vision, vol. 1, pp. 1135–1141 (2005)Google Scholar
  9. 9.
    Kakadiaris, I., Metaxas, D.: Model-based estimation of 3d human motion. IEEE Transactions on Pattern Analysis and Machine Intelligence 22(12), 1453–1459 (2000)CrossRefGoogle Scholar
  10. 10.
    Drummond, T., Cipolla, R.: Real-time visual tracking of complex structures. IEEE Trans. Pattern Analalysis Machine Intelligence 24(7), 932–946 (2002)CrossRefGoogle Scholar
  11. 11.
    Martin, F., Horaud, R.: Multiple camera tracking of rigid objects. International Journal of Robotics Research 21(2), 97–113 (2002)CrossRefGoogle Scholar
  12. 12.
    Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Analysis and Machine Intelligence 8(6), 679–698 (1986)CrossRefGoogle Scholar
  13. 13.
    Perona, P.: Steerable-scalable kernels for edge detection and junction analysis. In: European Conference on Computer Vision, pp. 3–18 (1992),
  14. 14.
    Geusebroek, J.M., Smeulders, A.W.M., van de Weijer, J.: Fast anisotropic gauss filtering. IEEE Trans. Image Processing 12(8), 938–943 (2003)CrossRefGoogle Scholar
  15. 15.
    Ronfard, R.: Region based strategies for active contour models. International Journal of Computer Vision 13(2), 229–251 (1994), CrossRefGoogle Scholar
  16. 16.
    van de Weijer, J., Gevers, T.: Tensor based feature detection for color images. In: Proc. IS&TSID’s CIC 2004, Scottsdale, Arizona, USA (2004)Google Scholar
  17. 17.
    Knossow, D., Ronfard, R., Horaud, R., Devernay, F.: Tracking with the kinematics of extremal contours. In: Narayanan, P.J., Nayar, S.K., Shum, H.-Y. (eds.) ACCV 2006. LNCS, vol. 3851, pp. 664–673. Springer, Heidelberg (2006), CrossRefGoogle Scholar
  18. 18.
    Murray, R.M., Li, Z., Sastry, S.S.: A Mathematical Introduction to Robotic Manipulation. CRC Press, Ann Arbor (1994)zbMATHGoogle Scholar
  19. 19.
    Di Zenzo, S.: Note: A note on the gradient of a multi-image. Computer Vision, Graphics, and Image Processing 33(1), 116–125 (1986)CrossRefGoogle Scholar
  20. 20.
    Koenderink, J.J., van Doorn, A.J.: Receptive field families. Biol. Cybern. 63, 291–297 (1990)zbMATHCrossRefGoogle Scholar
  21. 21.
    Triggs, B., Sdika, M.: Boundary conditions for young - van vliet recursive filtering. IEEE Transactions on Signal Processing (To appear, 2006)Google Scholar
  22. 22.
    Young, I.T., van Vliet, L.J.: Recursive implementation of the gaussian filter, signal processing. Signal Processing 44(2), 139–151 (1995)CrossRefGoogle Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • David Knossow
    • 1
  • Joost van de Weijer
    • 1
  • Radu Horaud
    • 1
  • Rémi Ronfard
    • 1
  1. 1.INRIA Rhône-Alpes, 655 Av. de l’Europe, 38330 MontbonnotFrance

Personalised recommendations