Deterministic 3D Human Pose Estimation Using Rigid Structure

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6313)


This paper explores a method, first proposed by Wei and Chai [1], for estimating 3D human pose from several frames of uncalibrated 2D point correspondences containing projected body joint locations. In their work Wei and Chai boldly claimed that, through the introduction of rigid constraints to the torso and hip, camera scales, bone lengths and absolute depths could be estimated from a finite number of frames (i.e. ≥ 5). In this paper we show this claim to be false, demonstrating in principle one can never estimate these parameters in a finite number of frames. Further, we demonstrate their approach is only valid for rigid sub-structures of the body (e.g. torso). Based on this analysis we propose a novel approach using deterministic structure from motion based on assumptions of rigidity in the body’s torso. Our approach provides notably more accurate estimates and is substantially faster than Wei and Chai’s approach, and unlike the original, can be solved as a deterministic least-squares problem.


Rigid Structure Bone Length Deterministic Structure Rigid Constraint Motion Approach 
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.
    Wei, X.K., Chai, J.: Modeling 3D human poses from uncalibrated monocular images. In: IEEE International Conference on Computer Vision (2009)Google Scholar
  2. 2.
    Agarwal, A., Triggs, B.: 3D Human pose from silhouettes by relevance vector regression. In: IEEE Conference on Computer Vision and Pattern Recognition (2004)Google Scholar
  3. 3.
    Taylor, C.J.: Reconstruction of articulated objects from point correspondences in a single uncalibrated image. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 677–684 (2000)Google Scholar
  4. 4.
    Barron, C., Kakadiaris, I.A.: Estimating anthropometry and pose from a single image. In: IEEE Conference on Computer Vision and Pattern Recognition (2000)Google Scholar
  5. 5.
    Bregler, C., Hertzmann, A., Biermann, H.: Recovering non-rigid 3D shape from image streams. In: IEEE Conference on Computer Vision and Pattern Recognition (2000)Google Scholar
  6. 6.
    Tomasi, C., Kanade, T.: Shape and motion from image streams under orthography: a factorization method. International Journal of Computer Vision 9, 137–154 (1992)CrossRefGoogle Scholar
  7. 7.
    Torresani, L., Hertzmann, A., Bregler, C.: Learning non-rigid 3D shape from 2D motion. In: NIPS (2005)Google Scholar
  8. 8.
    Xiao, J., Chai, J., Kanade, T.: A closed form solution to non-rigid shape and motion recovery. International Journal of Computer Vision 67, 233–246 (2006)CrossRefGoogle Scholar
  9. 9.
    Torresani, L., Hertzmann, A., Bregler, C.: Non-rigid structure from motion: Estimating shape and motion with hierarchical priors. IEEE Transactions on Pattern Analysis and Machine Intelligence 30, 878–892 (2008)CrossRefGoogle Scholar
  10. 10.
    Akhter, I., Sheikh, Y., Khan, S., Kanade, T.: Nonrigid structure from motion in trajectory space. In: NIPS (2008)Google Scholar
  11. 11.
    Ullman, S.: The interpretation of visual motion (1979)Google Scholar
  12. 12.
    Morita, T., Kanade, T.: A sequential factorization method for recovering shape and motion from image streams. IEEE Transactions on Pattern Analysis and Machine Intelligence 18, 858–867 (1996)Google Scholar
  13. 13.
    Hajder, L., Chetverikov, D., Vajk, I.: Robust structure from motion under weak perspective. 3D Data Processing, Visualization and Transmission (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  1. 1.University of Queensland, Australia 
  2. 2.Commonwealth Scientific and Industrial Research Organisation (CSIRO)Australia

Personalised recommendations