Gaussian Process Latent Variable Models for Human Pose Estimation

  • Carl Henrik Ek
  • Philip H. S. Torr
  • Neil D. Lawrence
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4892)


We describe a method for recovering 3D human body pose from silhouettes. Our model is based on learning a latent space using the Gaussian Process Latent Variable Model (GP-LVM) [1] encapsulating both pose and silhouette features Our method is generative, this allows us to model the ambiguities of a silhouette representation in a principled way. We learn a dynamical model over the latent space which allows us to disambiguate between ambiguous silhouettes by temporal consistency. The model has only two free parameters and has several advantages over both regression approaches and other generative methods. In addition to the application shown in this paper the suggested model is easily extended to multiple observation spaces without constraints on type.


Latent Space Joint Angle Latent Representation Marginal Likelihood Latent Variable 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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lawrence, N.D.: Probabilistic non-linear principal component analysis with gaussian process latent variable models. Journal of Machine Learning Research 6, 1783–1816 (2005)MathSciNetGoogle Scholar
  2. 2.
    Agarwal, A., Triggs, B.: Recovering 3d human pose from monocular images. IEEE Trans. Pattern Anal. Mach. Intell. 28(1), 44–58 (2006)CrossRefGoogle Scholar
  3. 3.
    Grauman, K., Shakhnarovich, G., Darrell, T.: Inferring 3d structure with a statistical image-based shape model. In: ICCV 2003, pp. 641–648 (2003)Google Scholar
  4. 4.
    Kehl, R., Bray, M., Gool, L.J.V.: Full body tracking from multiple views using stochastic sampling. In: CVPR(2), pp. 129–136 (2005)Google Scholar
  5. 5.
    Sminchisescu, C., Kanaujia, A., Li, Z., Metaxas, D.N.: Discriminative density propagation for 3d human motion estimation. In: CVPR (1), pp. 390–397 (2005)Google Scholar
  6. 6.
    Sminchisescu, C., Telea, A.: Human pose estimation from silhouettes - a consistent approach using distance level sets. In: WSCG, pp. 413–420 (2002)Google Scholar
  7. 7.
    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
  8. 8.
    de Campos, T.E., Murray, D.W.: Regression-based hand pose estimation from multiple cameras. In: CVPR(1), pp. 782–789 (2006)Google Scholar
  9. 9.
    Sun, Y., Bray, M., Thayananthan, A., Yuan, B., Torr, P.: Regression-based human motion capture from voxel data. In: BMVC (2006)Google Scholar
  10. 10.
    Belongie, S., Malik, J., Puzicha, J.: Shape context: A new descriptor for shape matching and object recognition. In: NIPS, pp. 831–837 (2000)Google Scholar
  11. 11.
    Mori, G., Belongie, S.J., Malik, J.: Efficient shape matching using shape contexts. IEEE Trans. Pattern Anal. Mach. Intell. 27(11), 1832–1837 (2005)CrossRefGoogle Scholar
  12. 12.
    Rasmussen, C.E., Williams, C.K.: Gaussian Processes for Machine Learning. MIT Press, Cambridge (2006)Google Scholar
  13. 13.
    Lawrence, N.D.: Gaussian process latent variable models for visualisation of high dimensional data. In: NIPS (2003)Google Scholar
  14. 14.
    Lawrence, N.D., Candela, J.Q.: Local distance preservation in the gp-lvm through back constraints. In: ICML, pp. 513–520 (2006)Google Scholar
  15. 15.
    Wang, J., Fleet, D.J., Hertzmann, A.: Gaussian process dynamical models. In: NIPS (2005)Google Scholar
  16. 16.
    Shon, A.P., Grochow, K., Hertzmann, A., Rao, R.P.N.: Learning shared latent structure for image synthesis and robotic imitation. In: NIPS (2005)Google Scholar
  17. 17.
    Viterbi, A.J.: Error bounds for convolutional codes and an asymptotical optimum decoding algorithm. IEEE Transactions on Information Theory (1967)Google Scholar
  18. 18.
    Shakhnarovich, G., Viola, P.A., Darrell, T.: Fast pose estimation with parameter-sensitive hashing. In: ICCV, pp. 750–759 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Carl Henrik Ek
    • 1
  • Philip H. S. Torr
    • 1
  • Neil D. Lawrence
    • 2
  1. 1.Department of ComputingOxford Brookes UniversityUnited Kingdom
  2. 2.School of Computer ScienceUniversity of ManchesterUnited Kingdom

Personalised recommendations