Foreground Consistent Human Pose Estimation Using Branch and Bound

  • Jens Puwein
  • Luca Ballan
  • Remo Ziegler
  • Marc Pollefeys
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8693)


We propose a method for human pose estimation which extends common unary and pairwise terms of graphical models with a global foreground term. Given knowledge of per pixel foreground, a pose should not only be plausible according to the graphical model but also explain the foreground well.

However, while inference on a standard tree-structured graphical model for pose estimation can be computed easily and very efficiently using dynamic programming, this no longer holds when the global foreground term is added to the problem.

We therefore propose a branch and bound based algorithm to retrieve the globally optimal solution to our pose estimation problem. To keep inference tractable and avoid the obvious combinatorial explosion, we propose upper bounds allowing for an intelligent exploration of the solution space.

We evaluated our method on several publicly available datasets, showing the benefits of our method.


Priority Queue Foreground Region Pairwise Term Global Branch Pose Estimation Problem 
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.

Supplementary material

978-3-319-10602-1_21_MOESM1_ESM.avi (2.6 mb)
Electronic Supplementary Material (AVI 2,692 KB)


  1. 1.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proc. CVPR (2005)Google Scholar
  2. 2.
    Eichner, M., Marin-Jimenez, M., Zisserman, A., Ferrari, V.: 2d articulated human pose estimation and retrieval in (almost) unconstrained still images. In: IJCV (2012)Google Scholar
  3. 3.
    Eichner, M., Ferrari, V.: Appearance sharing for collective human pose estimation. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012, Part I. LNCS, vol. 7724, pp. 138–151. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  4. 4.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Pictorial structures for object recognition. IJCV (2005)Google Scholar
  5. 5.
    Ferrari, V., Marin-Jiminez, M., Zisserman, A.: Progressive search space reduction for human pose estimation. In: Proc. CVPR (2008)Google Scholar
  6. 6.
    Johnson, S., Everingham, M.: Clustered pose and nonlinear appearance models for human pose estimation. In: Proc. BMVC (2010)Google Scholar
  7. 7.
    Kohli, P., Rihan, J., Bray, M., Torr, P.H.S.: Simultaneous segmentation and pose estimation of humans using dynamic graph cuts. IJCV (2008)Google Scholar
  8. 8.
    Ladicky, L., Torr, P.H.S., Zisserman, A.: Human pose estimation using a joint pixel-wise and part-wise formulation. In: Proc. CVPR (2013)Google Scholar
  9. 9.
    Lampert, C.H., Blaschko, M.B., Hofmann, T.: Efficient subwindow search: a branch and bound framework for object localization. TPAMI (2009)Google Scholar
  10. 10.
    Land, A.H., Doig, A.G.: An automatic method of solving discrete programming problems. Econometrica (1960)Google Scholar
  11. 11.
    Mori, G.: Guiding model search using segmentation. In: Proc. ICCV (2005)Google Scholar
  12. 12.
    Park, D., Ramanan, D.: N-best maximal decoders for part models. In: Proc. ICCV (2011)Google Scholar
  13. 13.
    Pishchulin, L., Jain, A., Andriluka, M., Thormaehlen, T., Schiele, B.: Articulated people detection and pose estimation: Reshaping the future. In: Proc. CVPR (2012)Google Scholar
  14. 14.
    Pishchulin, L., Andriluka, M., Gehler, P., Schiele, B.: Strong appearance and expressive spatial models for human pose estimation. In: Proc. ICCV (2013)Google Scholar
  15. 15.
    Rauschert, I., Collins, R.T.: A generative model for simultaneous estimation of human body shape and pixel-level segmentation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part V. LNCS, vol. 7576, pp. 704–717. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  16. 16.
    Rother, C., Kolmogorov, V., Blake, A.: ‘grabcut’ - interactive foreground extraction using iterated graph cuts. In: Proc. of ACM SIGGRAPH (2004)Google Scholar
  17. 17.
    Sapp, B., Weiss, D., Taskar, B.: Parsing human motion with stretchable models. In: CVPR (2011)Google Scholar
  18. 18.
    Sigal, L., Black, M.J.: Measure locally, reason globally: Occlusion-sensitive articulated pose estimation. In: Proc. CVPR (2006)Google Scholar
  19. 19.
    Singh, V.K., Nevatia, R., Huang, C.: Efficient inference with multiple heterogeneous part detectors for human pose estimation. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part III. LNCS, vol. 6313, pp. 314–327. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  20. 20.
    Sun, M., Telaprolu, M., Lee, H., Savarese, S.: An efficient branch-and-bound algorithm for optimal human pose estimation. In: Proc. CVPR (2012)Google Scholar
  21. 21.
    Taskar, B., Guestrin, C., Koller, D.: Max-margin markov networks. In: Proc. NIPS (2003)Google Scholar
  22. 22.
    Tian, T., Sclaroff, S.: Fast globally optimal 2d human detection with loopy graph models. In: Proc. CVPR (2010)Google Scholar
  23. 23.
    Tsochantaridis, I., Hofmann, T., Joachims, T., Altun, Y.: Support vector machine learning for interdependent and structured output spaces. In: Proc. ICML (2004)Google Scholar
  24. 24.
    Vahid, K., Sullivan, J.: Using richer models for articulated pose estimation of footballers. In: Proc. BMVC (2012)Google Scholar
  25. 25.
    Yang, Y., Ramanan, D.: Articulated human detection with flexible mixtures of parts. TPAMI (2013)Google Scholar
  26. 26.
    Zhang, X., Li, C., Tong, X., Hu, W., Maybank, S., Zhang, Y.: Efficient human pose estimation via parsing a tree structure based human model. In: Proc. ICCV (2009)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Jens Puwein
    • 1
  • Luca Ballan
    • 1
  • Remo Ziegler
    • 2
  • Marc Pollefeys
    • 1
  1. 1.Department of Computer ScienceETH ZurichSwitzerland
  2. 2.VizrtNorway

Personalised recommendations