Advertisement

Multi-activity Tracking in LLE Body Pose Space

  • Tobias Jaeggli
  • Esther Koller-Meier
  • Luc Van Gool
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4814)

Abstract

We present a method to simultaneously estimate 3d body pose and action categories from monocular video sequences. Our approach learns a low-dimensional embedding of the pose manifolds using Locally Linear Embedding (LLE), as well as the statistical relationship between body poses and their image appearance. In addition, the dynamics in these pose manifolds are modelled. Sparse kernel regressors capture the nonlinearities of these mappings efficiently. Body poses are inferred by a recursive Bayesian sampling algorithm with an activity-switching mechanism based on learned transfer functions. Using a rough foreground segmentation, we compare Binary PCA and distance transforms to encode the appearance. As a postprocessing step, the globally optimal trajectory through the entire sequence is estimated, yielding a single pose estimate per frame that is consistent throughout the sequence. We evaluate the algorithm on challenging sequences with subjects that are alternating between running and walking movements. Our experiments show how the dynamical model helps to track through poorly segmented low-resolution image sequences where tracking otherwise fails, while at the same time reliably classifying the activity type.

Keywords

Image Descriptor Locally Linear Embedding Relevance Vector Machine Nonlinear Dimensionality Reduction Appearance Descriptor 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Rosales, R., Sclaroff, S.: Learning body pose via specialized maps. In: NIPS (2001)Google Scholar
  2. 2.
    Thayananthan, A., Navaratnam, R., Stenger, B., Torr, P., Cipolla, R.: Multivariate relevance vector machines for tracking. In: Ninth European Conference on Computer Vision (2006)Google Scholar
  3. 3.
    Sminchisescu, C., Kanaujia, A., Li, Z., Metaxas, D.: Discriminative density propagation for 3d human motion estimation. In: CVPR (2005)Google Scholar
  4. 4.
    Agarwal, A., Triggs, B.: Monocular human motion capture with a mixture of regressors. In: IEEE Workshop on Vision for Human-Computer Interaction at CVPR, IEEE Computer Society Press, Los Alamitos (2005)Google Scholar
  5. 5.
    Isard, M., Blake, A.: Condensation - conditional density propagation for visual tracking. Int. J. Computer Vision (1998)Google Scholar
  6. 6.
    Doucet, A., Godsill, S., Andrieu, C.: On sequentional monte carlo sampling methods for bayesian filtering. Statistics and Computing (2000)Google Scholar
  7. 7.
    Roweis, S., Saul, L.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)CrossRefGoogle Scholar
  8. 8.
    Forsyth, D.A., Arikan, O., Ikemoto, L., O’ Brien, D.R.J.: Computational studies of human motion: Part 1. Computer Graphics and Vision 1(2/3) (2006)Google Scholar
  9. 9.
    Agarwal, A., Triggs, B.: 3d human pose from silhouettes by relevance vector regression. In: CVPR (2004)Google Scholar
  10. 10.
    Grauman, K., Shakhnarovich, G., Darrel, T.: Inferring 3d structure with a statistical image-based shape model. In: ICCV (2003)Google Scholar
  11. 11.
    Sun, Y., Bray, M., Thayananthan, A., Yuanand, B., Torr, P.: Regression-based human motion capture from voxel data. In: Proceedings British Machine Vision Conference (2006)Google Scholar
  12. 12.
    Lim, H., Camps, O.I., Sznaier, M., Morariu, V.I.: Dynamic appearance modeling for human tracking. In: Conference on Computer Vision and Pattern Recognition, pp. 751–757 (2006)Google Scholar
  13. 13.
    Elgammal, A., Lee, C.S.: Inferring 3d body pose from silhouettes using activity manifold learning. In: CVPR (2004)Google Scholar
  14. 14.
    Wang, J.M., Fleet, D.J., Hertzmann, A.: Gaussian process dynamical models. Advances in Neural Information Processing Systems 18, 1441–1448 (2006)Google Scholar
  15. 15.
    Sminchisescu, C., Jepson, A.: Generative modeling for continuous non-linearly embedded visual inference. In: ICML (2004)Google Scholar
  16. 16.
    Li, R., Yang, M.H., Sclaroff, S., Tian, T.P.: Monocular tracking of 3d human motion with a coordinated mixture of factor analyzers. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 137–150. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  17. 17.
    Urtasun, R., Fleet, D.J., Fua, P.: 3d people tracking with gaussian process dynamical models. In: CVPR 2006. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 238–245. IEEE Computer Society Press, Los Alamitos (2006)Google Scholar
  18. 18.
    Jaeggli, T., Koller-Meier, E., Van Gool, L.: Monocular Tracking with a Mixture of View-Dependent Learned Models. In: Perales, F.J., Fisher, R.B. (eds.) AMDO 2006. LNCS, vol. 4069, Springer, Heidelberg (2006)Google Scholar
  19. 19.
    Isard, M., Blake, A.: A mixed-state CONDENSATION tracker with automatic model-switching. In: ICCV, pp. 107–112 (1998)Google Scholar
  20. 20.
    Tenenbaum, J.B., de Silva, V., Langford, J.C.: A Global Geometric Framework for Nonlinear Dimensionality Reduction. Science 290(5500), 2319–2323 (2000)CrossRefGoogle Scholar
  21. 21.
    Bailey, D.G.: An efficient euclidean distance transform. In: Klette, R., Žunić, J. (eds.) IWCIA 2004. LNCS, vol. 3322, Springer, Heidelberg (2004)Google Scholar
  22. 22.
    Zivkovic, Z., Verbeek, J.: Transformation invariant component analysis for binary images. In: CVPR (1), pp. 254–259 (2006)Google Scholar
  23. 23.
    Bhattacharyya, A.: On a measure of divergence between two statistical populations defined by their probability distributions. Bull. Calcutta Math Soc. (1943)Google Scholar
  24. 24.
    Kschischang, F., Frey, B.J., Loeliger, H.A.: Factor graphs and the sum-product algorithm. IEEE Trans. Info. Theory 47, 498–519 (2001)zbMATHCrossRefMathSciNetGoogle Scholar
  25. 25.
    Yedidia, J., Freeman, W., Weiss, Y.: Understanding belief propagation and its generalizations. Technical Report TR-2001-22, MERL (2002)Google Scholar
  26. 26.
    Sidenbladh, H., Black, M., Fleet, D.: Stochastic tracking of 3d human figures using 2d image motion. In: Vernon, D. (ed.) ECCV 2000. LNCS, pp. 702–718. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  27. 27.
    Tipping, M.: The relevance vector machine. In: NIPS (2000)Google Scholar
  28. 28.
    Sigal, L., Bhatia, S., Roth, S., Black, M., Isard, M.: Tracking loose-limbed people. In: CVPR (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Tobias Jaeggli
    • 1
  • Esther Koller-Meier
    • 1
  • Luc Van Gool
    • 1
    • 2
  1. 1.ETH Zurich, D-ITET/BIWI, CH-8092 Zurich 
  2. 2.Katholieke Universiteit Leuven, ESAT/VISICS, B-3001 Leuven 

Personalised recommendations