Pose Locality Constrained Representation for 3D Human Pose Reconstruction

  • Xiaochuan Fan
  • Kang Zheng
  • Youjie Zhou
  • Song Wang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8689)


Reconstructing 3D human poses from a single 2D image is an ill-posed problem without considering the human body model. Explicitly enforcing physiological constraints is known to be non-convex and usually leads to difficulty in finding an optimal solution. An attractive alternative is to learn a prior model of the human body from a set of human pose data. In this paper, we develop a new approach, namely pose locality constrained representation (PLCR), to model the 3D human body and use it to improve 3D human pose reconstruction. In this approach, the human pose space is first hierarchically divided into lower-dimensional pose subspaces by subspace clustering. After that, a block-structural pose dictionary is constructed by concatenating the basis poses from all the pose subspaces. Finally, PLCR utilizes the block-structural pose dictionary to explicitly encourage pose locality in human-body modeling – nonzero coefficients are only assigned to the basis poses from a small number of pose subspaces that are close to each other in the pose-subspace hierarchy. We combine PLCR into the matching-pursuit based 3D human-pose reconstruction algorithm and show that the proposed PLCR-based algorithm outperforms the state-of-the-art algorithm that uses the standard sparse representation and physiological regularity in reconstructing a variety of human poses from both synthetic data and real images.


3D human pose reconstruction subspace clustering hierarchical pose tree 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Di Franco, D.E., Cham, T.J., Rehg, J.M.: Reconstruction of 3D figure motion from 2D correspondences. In: CVPR (2001)Google Scholar
  2. 2.
    Elhamifar, E., Vidal, R.: Sparse subspace clustering. In: CVPR (2009)Google Scholar
  3. 3.
    Jenatton, R., Mairal, J., Obozinski, G., Bach, F.: Proximal methods for hierarchical sparse coding. The Journal of Machine Learning Research 12, 2297–2334 (2011)zbMATHMathSciNetGoogle Scholar
  4. 4.
    Lee, H.J., Chen, Z.: Determination of 3D human body postures from a single view. Computer Vision, Graphics, and Image Processing 30(2), 148–168 (1985)CrossRefGoogle Scholar
  5. 5.
    Li, R., Tian, T.P., Sclaroff, S., Yang, M.H.: 3D human motion tracking with a coordinated mixture of factor analyzers. IJCV 87(1-2), 170–190 (2010)CrossRefGoogle Scholar
  6. 6.
    Liebowitz, D., Carlsson, S.: Uncalibrated motion capture exploiting articulated structure constraints. IJCV 51(3), 171–187 (2003)CrossRefGoogle Scholar
  7. 7.
    Liu, G., Lin, Z., Yan, S., Sun, J., Yu, Y., Ma, Y.: Robust recovery of subspace structures by low-rank representation. TPAMI 35(1), 171–184 (2013)CrossRefGoogle Scholar
  8. 8.
    Liu, G., Lin, Z., Yu, Y.: Robust subspace segmentation by low-rank representation. In: ICML (2010)Google Scholar
  9. 9.
    Parameswaran, V., Chellappa, R.: View independent human body pose estimation from a single perspective image. In: CVPR (2004)Google Scholar
  10. 10.
    Raja, K., Laptev, I., Pérez, P., Oisel, L.: Joint pose estimation and action recognition in image graphs. In: ICIP (2011)Google Scholar
  11. 11.
    Ramakrishna, V., Kanade, T., Sheikh, Y.: Reconstructing 3D human pose from 2D image landmarks. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part IV. LNCS, vol. 7575, pp. 573–586. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  12. 12.
    Safonova, A., Hodgins, J.K., Pollard, N.S.: Synthesizing physically realistic human motion in low-dimensional, behavior-specific spaces. TOG 23(3), 514–521 (2004)CrossRefGoogle Scholar
  13. 13.
    Salzmann, M., Urtasun, R.: Implicitly constrained gaussian process regression for monocular non-rigid pose estimation. In: NIPS (2010)Google Scholar
  14. 14.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. TPAMI, 888–905 (2000)Google Scholar
  15. 15.
    Soltanolkotabi, M., Elhamifar, E., Candes, E.: Robust subspace clustering. arXiv preprint arXiv:1301.2603 (2013)Google Scholar
  16. 16.
    Taylor, C.J.: Reconstruction of articulated objects from point correspondences in a single uncalibrated image. In: CVPR (2000)Google Scholar
  17. 17.
    Valmadre, J., Lucey, S.: Deterministic 3D human pose estimation using rigid structure. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part III. LNCS, vol. 6313, pp. 467–480. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  18. 18.
    Vidal, R.: Subspace clustering. Signal Processing Magazine 28(2), 52–68 (2011)CrossRefGoogle Scholar
  19. 19.
    Wang, J., Yang, J., Yu, K., Lv, F., Huang, T., Gong, Y.: Locality-constrained linear coding for image classification. In: CVPR, pp. 3360–3367 (2010)Google Scholar
  20. 20.
    Wei, X.K., Chai, J.: Modeling 3D human poses from uncalibrated monocular images. In: ICCV (2009)Google Scholar
  21. 21.
    Yang, A.Y., Iyengar, S., Sastry, S., Bajcsy, R., Kuryloski, P., Jafari, R.: Distributed segmentation and classification of human actions using a wearable motion sensor network. In: CVPRW (2008)Google Scholar
  22. 22.
    Yao, A., Gall, J., Van Gool, L.: Coupled action recognition and pose estimation from multiple views. IJCV (2012)Google Scholar
  23. 23.
    Yu, T.H., Kim, T.K., Cipolla, R.: Unconstrained monocular 3D human pose estimation by action detection and cross-modality regression forest. In: CVPR (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Xiaochuan Fan
    • 1
  • Kang Zheng
    • 1
  • Youjie Zhou
    • 1
  • Song Wang
    • 1
  1. 1.Department of Computer Science & EngineeringUniversity of South CarolinaUSA

Personalised recommendations