Advertisement

Relevant Feature Selection for Human Pose Estimation and Localization in Cluttered Images

  • Ryuzo Okada
  • Stefano Soatto
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5303)

Abstract

We address the problem of estimating human body pose from a single image with cluttered background. We train multiple local linear regressors for estimating the 3D pose from a feature vector of gradient orientation histograms. Each linear regressor is capable of selecting relevant components of the feature vector depending on pose by training it on a pose cluster which is a subset of the training samples with similar pose. For discriminating the pose clusters, we use kernel Support Vector Machines (SVM) with pose-dependent feature selection. We achieve feature selection for kernel SVMs by estimating scale parameters of RBF kernel through minimization of the radius/margin bound, which is an upper bound of the expected generalization error, with efficient gradient descent. Human detection is also possible with these SVMs. Quantitative experiments show the effectiveness of pose-dependent feature selection to both human detection and pose estimation.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proc. of CVPR, vol. 2, pp. 886–893 (2006)Google Scholar
  2. 2.
    Mikolajczyk, K., Schmid, C., Zisserman, A.: Human detection based on a probabilistic assembly of robust part detectors. In: Proc. of ECCV, vol. I, pp. 69–81 (2004)Google Scholar
  3. 3.
    Zhu, Q., Avidan, S., Yeh, M.C., Cheng, K.T.: Fast human detection using a cascade of histograms of oriented gradients. In: Proc. of CVPR, vol. 2, pp. 1491–1498 (2006)Google Scholar
  4. 4.
    Agarwal, A., Triggs, B.: A local basis representation for estimating human pose from cluttered images. In: Proc. of ACCV, vol. 1, pp. 50–59 (2006)Google Scholar
  5. 5.
    Poppe, R.: Evaluating example-based pose estimation: experiments on the HumanEva sets. In: Computer Vision and Pattern Recognition (CVPR 2007) workshop on Evaluation of Articulated Human Motion and Pose Estimation (EHuM2) (2007)Google Scholar
  6. 6.
    Shakhnarovich, G., Viola, P., Darrell, T.: Fast pose estimation with parameter-sensitive hashing. In: Proc. of ICCV, vol. 2, pp. 750–757 (2007)Google Scholar
  7. 7.
    Blum, A., Langley, P.: Selection of relevant features and examples in machine learning. Artificial Intelligence 97(1-2), 245–271 (1997)MathSciNetCrossRefzbMATHGoogle Scholar
  8. 8.
    Agarwal, A., Triggs, B.: Monocular human motion capture with a mixture of regressors. In: IEEE Workshop on Vision for Human-Computer Interaction, pp. 1–8 (2005)Google Scholar
  9. 9.
    Thayananthan, A., Navaratnam, R., Stenger, B., Torr, P.H.S., Cipolla, R.: Multivariate relevance vector machines for tracking. In: Proc. of ECCV, Graz, Austria, vol. 3, pp. 124–138 (May 2006)Google Scholar
  10. 10.
    Vapnik, V.N.: Statistical Learning Theory. Wiley-Interscience, Chichester (1998)zbMATHGoogle Scholar
  11. 11.
    Keerthi, S.S.: Efficient tuning of SVM hyperparameters using radius/margin bound and iterative algorithms. IEEE Trans. on Neural Networks 13(5), 1225–1229 (2002)CrossRefGoogle Scholar
  12. 12.
    Bissacco, A., Yang, M.H., Soatto, S.: Fast human pose estimation using appearance and motion via multi-dimensional boosting regression. In: Proc. of CVPR, pp. 1–8 (2007)Google Scholar
  13. 13.
    Date, N., et al.: Real-time human motion sensing based on vision-based inverse kinematics for interactive applications. In: Proc. of ICPR, vol. 3, pp. 318–321 (2004)Google Scholar
  14. 14.
    Sigal, L., Bhatia, S., Roth, S., Black, M.J., Isard, M.: Tracking loose-limbed people. In: Proc. of CVPR, vol. I, pp. 421–428 (2004)Google Scholar
  15. 15.
    Sigal, L., Black, M.J.: Predicting 3D people from 2D pictures. In: Proc. of Conf. Articulated Motion and Deformable Objects, pp. 185–195 (2006)Google Scholar
  16. 16.
    Wren, C.R., Azarbayejani, A., Darrell, T., Pentland, A.P.: Pfinder: Real-time tracking of the human body. IEEE Trans. on PAMI 19(7), 780–785 (1997)CrossRefGoogle Scholar
  17. 17.
    Agarwal, A., Triggs, B.: Recovering 3D human pose from monocular images. IEEE Trans. on PAMI 28(1), 44–58 (2006)CrossRefGoogle Scholar
  18. 18.
    Okada, R., Stenger, B., Kondoh, N.: A video motion capture system for interactive games. In: Proc. of MVA, pp. 186–189 (2007)Google Scholar
  19. 19.
    Sminchisescu, C., Kanaujia, A., Li, Z., Metaxas, D.: Learning to reconstruct 3D human motion from bayesian mixtures of experts. a probabilistic discriminative approach. Technical Report CSRG-502, University of Toronto (2004)Google Scholar
  20. 20.
    Viola, P., Jones, M., Snow, D.: Detecting pedestrians using patterns of motion and appearance. In: Proc. of ICCV, pp. 734–741 (2003)Google Scholar
  21. 21.
    Sabzmeydani, P., Mori, G.: Detecting pedestrians by learning shapelet features. In: Proc. of CVPR, pp. 1–8 (2007)Google Scholar
  22. 22.
    Zehnder, P., Koller-Meier, E., Gool, L.V.: A hierarchical system for recognition, tracking and pose estimation. In: Bengio, S., Bourlard, H. (eds.) MLMI 2004. LNCS, vol. 3361, pp. 329–340. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  23. 23.
    Evgeniou, T., Pontil, M., Papageorgiou, C., Poggio, T.: Image representations for object detection using kernel classifiers. In: Proc. of ACCV, pp. 687–692 (2000)Google Scholar
  24. 24.
    Platt, J.: Probabilistic outputs for support vector machines and comparison to regularize likelihood methods. In: Smola, A., Bartlett, P., Schoelkopf, B., Schuurmans, D. (eds.) Advances in Large Margin Classifiers, pp. 61–74 (2000)Google Scholar
  25. 25.
    Tipping, M.E.: Sparse bayesian learning and the relevance vector machine. Journal of Machine Learning Research 1, 211–244 (2001)MathSciNetzbMATHGoogle Scholar
  26. 26.
    Micchelli, C.A., Pontil, M.A.: On learning vector-valued functions. Neural Computation 17(1), 177–204 (2005)MathSciNetCrossRefzbMATHGoogle Scholar
  27. 27.
    Scholkopf, B., Smola, A.J.: Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT Press, Cambridge (2001)Google Scholar
  28. 28.
    Shanno, D.F., Phua, K.H.: Minimization of unconstrained multivarite functions. ACM Transactions on Mathematical Software 6, 618–622 (1980)CrossRefGoogle Scholar
  29. 29.
    Chapelle, O., Vapnik, V., Bousquet, O., Mukherjee, S.: Choosing multiple parameters for support vector machines. Machine Learning 46, 131–159 (2002)CrossRefzbMATHGoogle Scholar
  30. 30.
    Sigal, L., Black, M.J.: Humaneva: Synchronized video and motion capture dataset for evaluation of articulated human motion. Technical Report CS-06-08, Brown Univ. (2006), http://vision.cs.brown.edu/humaneva/
  31. 31.
    Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines (2001), http://www.csie.ntu.edu.tw/~cjlin/libsvm

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Ryuzo Okada
    • 1
  • Stefano Soatto
    • 1
  1. 1.Computer Science DepartmentUniversity of CaliforniaLos AngelesUSA

Personalised recommendations