Gaussian-Like Spatial Priors for Articulated Tracking

  • Søren Hauberg
  • Stefan Sommer
  • Kim Steenstrup Pedersen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6311)


We present an analysis of the spatial covariance structure of an articulated motion prior in which joint angles have a known covariance structure. From this, a well-known, but often ignored, deficiency of the kinematic skeleton representation becomes clear: spatial variance not only depends on limb lengths, but also increases as the kinematic chains are traversed. We then present two similar Gaussian-like motion priors that are explicitly expressed spatially and as such avoids any variance coming from the representation. The resulting priors are both simple and easy to implement, yet they provide superior predictions.


Tangent Space Joint Angle Kinematic Chain Average Standard Deviation Likelihood Model 
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.


  1. 1.
    Poppe, R.: Vision-based human motion analysis: An overview. Computer Vision and Image Understanding 108, 4–18 (2007)CrossRefGoogle Scholar
  2. 2.
    Cappé, O., Godsill, S.J., Moulines, E.: An overview of existing methods and recent advances in sequential Monte Carlo. Proceedings of the IEEE 95, 899–924 (2007)CrossRefGoogle Scholar
  3. 3.
    Erleben, K., Sporring, J., Henriksen, K., Dohlmann, H.: Physics Based Animation. Charles River Media (2005)Google Scholar
  4. 4.
    Zhao, J., Badler, N.I.: Inverse kinematics positioning using nonlinear programming for highly articulated figures. ACM Transaction on Graphics 13, 313–336 (1994)CrossRefGoogle Scholar
  5. 5.
    Nocedal, J., Wright, S.J.: Numerical optimization. Springer Series in Operations Research. Springer, Heidelberg (1999)zbMATHCrossRefGoogle Scholar
  6. 6.
    Brubaker, M.A., Fleet, D.J., Hertzmann, A.: Physics-based person tracking using the anthropomorphic walker. Int. J. of Comp. Vis. 87, 140–155 (2010)CrossRefGoogle Scholar
  7. 7.
    Wang, J.M., Fleet, D.J., Hertzmann, A.: Gaussian Process Dynamical Models for Human Motion. Pattern Analysis and Machine Intelligence 30, 283–298 (2008)CrossRefGoogle Scholar
  8. 8.
    Sminchisescu, C., Jepson, A.: Generative modeling for continuous non-linearly embedded visual inference. In: ICML ’04: Proceedings of the Twenty-First International Conference on Machine Learning, pp. 759–766. ACM, New York (2004)Google Scholar
  9. 9.
    Lu, Z., Carreira-Perpinan, M., Sminchisescu, C.: People Tracking with the Laplacian Eigenmaps Latent Variable Model. In: Platt, J., et al. (eds.) Advances in Neural Inf. Proc. Systems, vol. 20, pp. 1705–1712. MIT Press, Cambridge (2008)Google Scholar
  10. 10.
    Sidenbladh, H., Black, M.J., Fleet, D.J.: Stochastic tracking of 3d human figures using 2d image motion. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 702–718. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  11. 11.
    Elgammal, A.M., Lee, C.S.: Tracking People on a Torus. IEEE Transaction on Pattern Analysis and Machine Intelligence 31, 520–538 (2009)CrossRefGoogle Scholar
  12. 12.
    Urtasun, R., Fleet, D.J., Fua, P.: 3D People Tracking with Gaussian Process Dynamical Models. In: CVPR ’06: Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 238–245 (2006)Google Scholar
  13. 13.
    Carreira-Perpinan, M.A., Lu, Z.: The Laplacian Eigenmaps Latent Variable Model. JMLR W&P 2, 59–66 (2007)Google Scholar
  14. 14.
    Urtasun, R., Fleet, D.J., Hertzmann, A., Fua, P.: Priors for people tracking from small training sets. In: Int. Conf. on Comp. Vis., vol. 1, pp. 403–410 (2005)Google Scholar
  15. 15.
    Grochow, K., Martin, S.L., Hertzmann, A., Popović, Z.: Style-based inverse kinematics. ACM Transaction on Graphics 23, 522–531 (2004)CrossRefGoogle Scholar
  16. 16.
    Balan, A.O., Sigal, L., Black, M.J.: A quantitative evaluation of video-based 3d person tracking. Visual Surveillance and Performance Evaluation of Tracking and Surveillance, 349–356 (2005)Google Scholar
  17. 17.
    Bandouch, J., Engstler, F., Beetz, M.: Accurate human motion capture using an ergonomics-based anthropometric human model. In: Perales, F.J., Fisher, R.B. (eds.) AMDO 2008. LNCS, vol. 5098, pp. 248–258. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  18. 18.
    Pennec, X.: Probabilities and statistics on riemannian manifolds: Basic tools for geometric measurements. In: NSIP, pp. 194–198 (1999)Google Scholar
  19. 19.
    MacCormick, J., Isard, M.: Partitioned sampling, articulated objects, and interface-quality hand tracking. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 3–19. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  20. 20.
    Sigal, L., Bhatia, S., Roth, S., Black, M.J., Isard, M.: Tracking loose-limbed people. In: CVPR ’04: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 421–428 (2004)Google Scholar
  21. 21.
    Sommer, S., Lauze, F., Hauberg, S., Nielsen, M.: Manifold Valued Statistics, Exact Principal Geodesic Analysis and the Effect of Linear Approximations. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part VI. LNCS, vol. 6316, pp. 43–56. Springer, Heidelberg (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Søren Hauberg
    • 1
  • Stefan Sommer
    • 1
  • Kim Steenstrup Pedersen
    • 1
  1. 1.The eScience Centre, Dept. of Computer ScienceUniversity of Copenhagen 

Personalised recommendations