Efficient Inference with Multiple Heterogeneous Part Detectors for Human Pose Estimation

  • Vivek Kumar Singh
  • Ram Nevatia
  • Chang Huang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6313)


We address the problem of estimating human pose in a single image using a part based approach. Pose accuracy is directly affected by the accuracy of the part detectors but more accurate detectors are likely to be also more computationally expensive. We propose to use multiple, heterogeneous part detectors with varying accuracy and computation requirements, ordered in a hierarchy, to achieve more accurate and efficient pose estimation. For inference, we propose an algorithm to localize articulated objects by exploiting an ordered hierarchy of detectors with increasing accuracy. The inference uses branch and bound method to search for each part and use kinematics from neighboring parts to guide the branching behavior and compute bounds on the best part estimate. We demonstrate our approach on a publicly available People dataset and outperform the state-of-art methods. Our inference is 3 times faster than one based on using a single, highly accurate detector.


Part Detector Pictorial Structure Region Template Active Branch Perceptron Algorithm 
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.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Pictorial structures for object recognition. IJCV 61, 55–79 (2005)CrossRefGoogle Scholar
  2. 2.
    Hua, G., Yang, M.H., Wu, Y.: Learning to estimate human pose with data driven belief propagation. In: CVPR, vol. 2, pp. 747–754 (2005)Google Scholar
  3. 3.
    Zhang, J., Luo, J., Collins, R., Liu, Y.: Body localization in still images using hierarchical models and hybrid search. In: CVPR, pp. 1536–1543 (2006)Google Scholar
  4. 4.
    Ramanan, D., Sminchisescu, C.: Training deformable models for localization. In: CVPR, vol. 1, pp. 206–213 (2006)Google Scholar
  5. 5.
    Felzenszwalb, P., Mcallester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: CVPR (2008)Google Scholar
  6. 6.
    Ramanan, D.: Learning to parse images of articulated bodies. In: NIPS, vol. 19, pp. 1129–1136 (2007)Google Scholar
  7. 7.
    Andriluka, M., Roth, S., Schiele, B.: Pictorial structures revisited: People detection and articulated pose estimation. In: CVPR (2009)Google Scholar
  8. 8.
    Wang, Y., Mori, G.: Multiple tree models for occlusion and spatial constraints in human pose estimation. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 710–724. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  9. 9.
    Sigal, L., Roth, S., Black, M.J., Isard, M.: Tracking loose-limbed people. In: CVPR, pp. 421–428 (2004)Google Scholar
  10. 10.
    Ren, X., Berg, A.C., Malik, J.: Recovering human body configurations using pairwise constraints between parts. In: ICCV, pp. 824–831 (2005)Google Scholar
  11. 11.
    Jiang, H., Martin, D.: Global pose estimation using non-tree models. In: CVPR (2008)Google Scholar
  12. 12.
    Zhu, L., Chen, Y., Lu, Y., Lin, C., Yuille, A.: Max margin and/or graph learning for parsing the human body. In: CVPR (2008)Google Scholar
  13. 13.
    Chen, Y., Zhu, L., Lin, C., Yuille, A., Zhang, H.: Rapid inference on a novel and/or graph for object detection, segmentation and parsing. In: Advances in Neural Information Processing Systems 2008, pp. 289–296 (2008)Google Scholar
  14. 14.
    Lee, M., Nevatia, R.: Human pose tracking using multi-level structured models. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3953, pp. 368–381. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  15. 15.
    Ferrari, V., Marin-Jimenez, M., Zisserman, A.: Progressive search space reduction for human pose estimation. In: CVPR (2008)Google Scholar
  16. 16.
    Bourdev, L., Malik, J.: Poselets: Body part detectors trained using 3d human pose annotations. In: ICCV (2009)Google Scholar
  17. 17.
    Collins, M.: Discriminative training methods for hidden markov models: theory and experiments with perceptron algorithms. In: EMNLP (2002)Google Scholar
  18. 18.
    Lampert, C., Blaschko, M., Hofmann, T.: Beyond sliding windows: Object localization by efficient subwindow search. In: CVPR (2008)Google Scholar
  19. 19.
    Kschischang, F., Frey, B., Loeliger, H.A.: Factor graphs and the sum-product algorithm. IEEE Transactions on Information Theory 47, 498–519 (2001)zbMATHCrossRefMathSciNetGoogle Scholar
  20. 20.
    Huang, C., Nevatia, R.: High performance object detection by collaborative learning of joint ranking of granule features. In: CVPR (2010)Google Scholar
  21. 21.
    Dalal, N., Triggs, B.: Histogram of oriented gradients for human detection. In: CVPR, pp. 886–893 (2005)Google Scholar
  22. 22.
    Wu, B., Nevatia, R.: Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors. In: ICCV, pp. 90–97 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Vivek Kumar Singh
    • 1
  • Ram Nevatia
    • 1
  • Chang Huang
    • 1
  1. 1.University of Southern CaliforniaLos AngelesUSA

Personalised recommendations