Advertisement

Easy Minimax Estimation with Random Forests for Human Pose Estimation

  • P. Daphne TsatsoulisEmail author
  • David Forsyth
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8925)

Abstract

We describe a method for human parsing that is straightforward and competes with state-of-the-art performance on standard datasets. Unlike the state-of-the-art, our method does not search for individual body parts or poselets. Instead, a regression forest is used to predict a body configuration in body-space. The output of this regression forest is then combined in a novel way. Instead of averaging the output of each tree in the forest we use minimax to calculate optimal weights for the trees. This optimal weighting improves performance on rare poses and improves the generalization of our method to different datasets. Our paper demonstrates the unique advantage of random forest representations: minimax estimation is straightforward with no significant retraining burden.

Keywords

Human pose estimation Regression Regression forests Minimax 

References

  1. 1.
    Yang, Y., Ramanan, D.: Articulated pose estimation using flexible mixtures of parts. In: CVPR (2011)Google Scholar
  2. 2.
    Wang, Y., Tran, D., Liao, Z.: Learning hierarchical poselets for human parsing. In: CVPR (2011)Google Scholar
  3. 3.
    Tran, D., Forsyth, D.: Improved human parsing with a full relational model. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 227–240. Springer, Heidelberg (2010) CrossRefGoogle Scholar
  4. 4.
    Eichner, M., Ferrari, V.: Better appearance models for pictorial structures. In: IICCV (2009)Google Scholar
  5. 5.
    Sapp, B., Toshev, A., Taskar, B.: Cascaded models for articulated pose estimation. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol. 6312, pp. 406–420. Springer, Heidelberg (2010) CrossRefGoogle Scholar
  6. 6.
    Andriluka, M., Roth, S., Schiele, B.: Pictorial structures revisited: People detection and articulated pose estimation. In: CVPR (2009)Google Scholar
  7. 7.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Pictorial structures for object recognition. IJCV 61(1), 55–79 (2005)CrossRefGoogle Scholar
  8. 8.
    Ioffe, S., Forsyth, D.: Human tracking with mixtures of trees. In: ICCV, pp. 690–695 (2001)Google Scholar
  9. 9.
    Ramanan, D.: Learning to parse images of articulated bodies. In: ANIPS, vol. 19, pp. 1129–1136 (2006)Google Scholar
  10. 10.
    Jiang, H., Martin, D.R.: Globel pose estimation using non-tree models. In: CVPR (2008)Google Scholar
  11. 11.
    Ren, X., Berg, A., Malik, J.: Recovering human body configurations using pairwise constraints between parts. In: IICCV, vol. 1, pp. 824–831 (2005)Google Scholar
  12. 12.
    Tian, T.P., Sclaroff, S.: Fast globally optimal 2D human detection with loopy graph models. In: CVPR (2010)Google Scholar
  13. 13.
    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
  14. 14.
    Mori, G., Ren, X., Efros, A., Malik, J.: Recovering human body configuration: Combining segmentation and recognition. In: CVPR, vol. 2, pp. 326–333 (2004)Google Scholar
  15. 15.
    Ferrari, V., Marín-Jiménez, M., Zisserman, A.: Progressive search space reduction for human pose estimation. In: CVPR (2008)Google Scholar
  16. 16.
    Felzenszwalb, P.F., Girshick, R.B., McAllester, D.: Cascade object detection with deformable part models. In: CVPR (2010)Google Scholar
  17. 17.
    Eichner, M., Ferrari, V.: Better appearance models for pictorial structures. In: BMVC (2009)Google Scholar
  18. 18.
    Bourdev, L., Malik, J.: Poselets: Body part detectors training using 3D human pose annotations. In: IICCV (2009)Google Scholar
  19. 19.
    Brox, T., Bourdev, L., Maji, S., Malik, J.: Object segmentation by alignment of poselet activations to image contours. In: CVPR (2011)Google Scholar
  20. 20.
    Bourdev, L., Maji, S., Malik, J.: Describing people: Poselet-based attribute classification. In: ICCV (2011)Google Scholar
  21. 21.
    Gkioxari, G., Arbelaez, P., Bourdev, L.D., Malik, J.: Articulated pose estimation using discriminative armlet classifiers. In: CVPR, pp. 3342–3349 (2013)Google Scholar
  22. 22.
    Jammalamadaka, N., Zisserman, A., Eichner, M., Ferrari, V., Jawahar, C.V.: Video retrieval by mimicking poses. In: ACM ICMR (2012)Google Scholar
  23. 23.
    Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipman, A., Blake, A.: Real-time human pose recognition in parts from single depth images. In: CVPR (2011)Google Scholar
  24. 24.
    Dantone, M., Gall, J., Leistner, C., van Gool, L.: Human pose estimation from still images using body parts dependent joint regressors. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2013) (to appear)Google Scholar
  25. 25.
    Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: CVPR 2011 (June 2011)Google Scholar
  26. 26.
    Ramanan, D., Forsyth, D.: Finding and tracking people from the bottom up. In: Proc. CVPR (2003)Google Scholar
  27. 27.
    Ferrari, V., Marin, M., Zisserman, A.: Pose search: retrieving people using their pose. In: CVPR (2009)Google Scholar
  28. 28.
    Taylor, C.: Reconstruction of articulated objects from point correspondences in a single uncalibrated image. In: CVPR, pp. 677–684 (2000)Google Scholar
  29. 29.
    Kakadiaris, I., Metaxas, D.: Model-based estimation of 3D human motion with occlusion based on active multi-viewpoint selection. In: CVPR, pp. 81–87 (1996)Google Scholar
  30. 30.
    Ikizler, N., Forsyth, D.: Searching video for complex activities with finite state models. In: CVPR (2007)Google Scholar
  31. 31.
    Sapp, B., Taskar, B.: Modec: Multimodal decomposable models for human pose estimation. In: Proc. CVPR (2013)Google Scholar
  32. 32.
    Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 898–916 (2011)CrossRefGoogle Scholar
  33. 33.
    Eichner, M., Marin-Jimenez, M., Zisserman, A., Ferrari, V.: 2D articulated human pose estimation and retrieval in (almost) unconstrained still images. In: ETH Zurich, D-ITET, BIWI, Technical Report No.272 (2010)Google Scholar
  34. 34.
    Sapp, B., Jordan, C., Taskar, B.: Adaptive pose priors for pictorial structures. In: CVPR (2010)Google Scholar
  35. 35.
    Yang, Y., Ramanan, D.: Articulated pose estimation using flexible mixtures of parts. In: IEEE PAMI (to appear)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of Illinois at Urbana-ChampaignChampaignUSA

Personalised recommendations