Skip to main content
SpringerLink
Log in
Book cover

Asian Conference on Computer Vision

ACCV 2014: Computer Vision -- ACCV 2014 pp 242–256Cite as

Regularity Guaranteed Human Pose Correction

  • Conference paper
  • First Online:

  • 2603 Accesses

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 9004))

Abstract

Benefited from the advantages provided by depth sensors, 3D human pose estimation has become feasible. However, the current estimation systems usually yield poor results due to severe occlusion and sensor noise in depth data. In this paper, we focus on a post-process step, pose correction, which takes the initial estimated poses as the input and deliver more reliable results. Although the regression based correction approach [1] has shown its effectiveness in decreasing the estimated errors, it cannot guarantee the regularity of corrected poses. To address this issue, we formulate pose correction as an optimization problem, which combines the output of the regression model with a pose prior model learned on a pre-captured motion data set. By considering the complexity and the geometric property of the pose data, the pose prior is estimated by von Mises-Fisher distributions in subspaces following divide-and-conquer strategies. By introducing the pose prior into our optimization framework, the regularity of the corrected poses is guaranteed. The experimental results on a challenging data set demonstrate that the proposed pose correction approach not only improves the accuracy, but also outputs more regular poses, compared to the-state-of-the-art.

This is a preview of subscription content, log in via an institution.

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

Notes

  1. 1.

    The bias \(\varDelta \) should be normalized by the method proposed in [1] to eliminate the scale variances between individuals. While, for denotational simplicity, we do not involve the normalization factor in this paper.

References

  1. Shen, W., Deng, K., Bai, X., Leyvand, T., Guo, B., Tu, Z.: Exemplar-based human action pose correction and tagging. In: Proceedings of CVPR (2012)

    Google Scholar 

  2. Microsoft Corp. Kinect for XBOX 360. Redmond WA

    Google Scholar 

  3. Han, J., Shao, L., Xu, D., Shotton, J.: Enhanced computer vision with microsoft kinect sensor: a review. IEEE Trans. Cybern. 43, 1318–1334 (2013)

    Article  Google Scholar 

  4. Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipman, A., Blake, A.: Real-time human pose recognition in parts from a single depth image. In: Proceedings of CVPR (2011)

    Google Scholar 

  5. Ganapathi, V., Plagemann, C., Koller, D., Thrun, S.: Real time motion capture using a single time-of-flight camera. In: Proceedings of CVPR, pp. 755–762 (2010)

    Google Scholar 

  6. Ye, M., Wang, X., Yang, R., Ren, L., Pollefeys, M.: Accurate 3D pose estimation from a single depth image. In: Proceedings of ICCV (2011)

    Google Scholar 

  7. Baak, A., Müller, M., Bharaj, G., Seidel, H.P., Theobalt, C.: A data-driven approach for real-time full body pose reconstruction from a depth camera. In: Proceedings of ICCV (2011)

    Google Scholar 

  8. Girshick, R., Shotton, J., Kohli, P., Criminisi, A., Fitzgibbon, A.: Efficient regression of general-activity human poses from depth images. In: Proceedings of ICCV (2011)

    Google Scholar 

  9. Sun, M., Kohli, P., Shotton, J.: Conditional regression forests for human pose estimation. In: Proceedings of CVPR (2012)

    Google Scholar 

  10. Shum, H.P.H., Ho, E.S.L., Jiang, Y., Takagi, S.: Real-time posture reconstruction for microsoft kinect. IEEE Trans. Cybern. 43, 1357–1369 (2013)

    Article  Google Scholar 

  11. Shen, W., Deng, K., Bai, X., Leyvand, T., Guo, B., Tu, Z.: Exemplar-based human action pose correction. IEEE Trans. Cybern. 44(7), 1053–1066 (2014)

    Article  Google Scholar 

  12. Wang, X., Zhang, Z., Ma, Y., Bai, X., Liu, W., Tu, Z.: Robust subspace discovery via relaxed rank minimization. Neural Comput. 26, 611–635 (2014)

    Article  MathSciNet  Google Scholar 

  13. Wang, B., Tu, Z.: Sparse subspace denoising for image manifolds. In: Proceedings of CVPR, pp. 468–475 (2013)

    Google Scholar 

  14. Bentley, J.L.: Multidimensional divide-and-conquer. Commun. ACM 23, 214–229 (1980)

    Article  MATH  MathSciNet  Google Scholar 

  15. Fisher, N.I., Lewis, T., Embleton, B.J.J.: Statistical Analysis of Spherical Data. Cambridge University Press, Cambridge (1993)

    MATH  Google Scholar 

  16. Wang, X., Bai, X., Ma, T., Liu, W., Latecki, L.J.: Fan shape model for object detection. In: Proceedings of CVPR, pp. 151–158 (2012)

    Google Scholar 

  17. Plagemann, C., Ganapathi, V., Koller, D., Thrun, S.: Real-time identification and localization of body parts from depth images. In: Proceedings of ICRA, pp. 3108–3113 (2010)

    Google Scholar 

  18. Breiman, L.: Random forests. Mach. Learn. 45, 5–32 (2001)

    Article  MATH  Google Scholar 

  19. Quinlan, J.R.: Induction of decision trees. Mach. Learn. 1, 81–106 (1986)

    Google Scholar 

  20. Ganapathi, V., Plagemann, C., Koller, D., Thrun, S.: Real-time human pose tracking from range data. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VI. LNCS, vol. 7577, pp. 738–751. Springer, Heidelberg (2012)

    Chapter  Google Scholar 

  21. Felzenszwalb, P.F., Huttenlocher, D.P.: Pictorial structures for object recognition. Int. J. Comput. Vis. 61, 55–79 (2005)

    Article  Google Scholar 

  22. Ren, X., Berg, A.C., Malik, J.: Recovering human body configurations using pairwise constraints between parts. In: Proceedings of ICCV, pp. 824–831 (2005)

    Google Scholar 

  23. Ramanan, D.: Learning to parse images of articulated bodies. In: Proceedings of NIPS, pp. 1129–1136 (2006)

    Google Scholar 

  24. Dantone, M., Gall, J., Leistner, C., Gool, L.J.V.: Human pose estimation using body parts dependent joint regressors. In: Proceedings of CVPR, pp. 3041–3048 (2013)

    Google Scholar 

  25. Ladicky, L., Torr, P.H.S., Zisserman, A.: Human pose estimation using a joint pixel-wise and part-wise formulation. In: Proceedings of CVPR, pp. 3578–3585 (2013)

    Google Scholar 

  26. Yang, Y., Ramanan, D.: Articulated pose estimation with flexible mixtures-of-parts. In: Proceedings of CVPR, pp. 1385–1392 (2011)

    Google Scholar 

  27. Yao, C., Bai, X., Liu, W., Latecki, L.J.: Human detection using learned part alphabet and pose dictionary. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part V. LNCS, vol. 8693, pp. 251–266. Springer, Heidelberg (2014)

    Chapter  Google Scholar 

  28. Lehrmann, A.M., Gehler, P.V., Nowozin, S.: A non-parametric bayesian network prior of human pose. In: Proceedings of ICCV, pp. 1281–1288 (2013)

    Google Scholar 

  29. Murray, R.M., Li, Z., Sastry, S.S.: A Mathematical Introduction to Robotic Manipulation. CRC Press, Boca Raton (1994)

    MATH  Google Scholar 

  30. Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22, 888–905 (2000)

    Article  Google Scholar 

  31. Sra, S.: A short note on parameter approximation for von mises-fisher distributions: and a fast implementation of \(i_s(x)\). Comput. Stat. 27, 177–190 (2011)

    Article  MathSciNet  Google Scholar 

  32. Luo, Z.Q., Tseng, P.: On the convergence of the coordinate descent method for convex differentiable minimization. J. Optim. Theory Appl. 72, 7–35 (1992)

    Article  MATH  MathSciNet  Google Scholar 

  33. Rasmussen, C.E., Williams, C.: Gaussian Processes for Machine Learning. MIT Press, Cambridge (2006)

    MATH  Google Scholar 

  34. Schölkopf, B., Smola, A., Williamson, R., Bartlett, P.L.: New support vector algorithms. Neural Comput. 12, 1207–1245 (2000)

    Article  Google Scholar 

  35. Cao, X., Wei, Y., Wen, F., Sun, J.: Face alignment by explicit shape regression. In: Proceedings of CVPR, pp. 2887–2894 (2012)

    Google Scholar 

  36. Zhou, Y., Yang, Y., Yi, M., Bai, X., Liu, W., Latecki, L.J.: Online multiple targets detection and tracking from mobile robot in cluttered indoor environments with depth camera. IJPRAI 28(1) (2014)

    Google Scholar 

Download references

Acknowledgement

This work was supported in part by the National Natural Science Foundation of China under Grant 61303095, in part by Research Fund for the Doctoral Program of Higher Education of China under Grant 20133108120017, in part by Innovation Program of Shanghai Municipal Education Commission under Grant 14YZ018, in part by Innovation Program of Shanghai University under Grant SDCX2013012 and in part by Cultivation Fund for the Young Faculty of Higher Education of Shanghai under Grant ZZSD13005. We thank Microsoft Corporation for providing the skeleton data set used in our experiments.

Author information

Authors and Affiliations

  1. School of Communication and Information Engineering, Shanghai University, 149 Yanchang Road, Shanghai, 200072, People’s Republic of China

    Wei Shen, Rui Lei, Dan Zeng & Zhijiang Zhang

Authors
  1. Wei Shen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rui Lei
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Dan Zeng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zhijiang Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Wei Shen .

Editor information

Editors and Affiliations

  1. Technische Universität München, Garching, Bayern, Germany

    Daniel Cremers

  2. University of Adelaide, Adelaide, South Australia, Australia

    Ian Reid

  3. Keio University, Yokohama, Kanagawa, Japan

    Hideo Saito

  4. University of California at Merced, Merced, California, USA

    Ming-Hsuan Yang

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this paper

Cite this paper

Shen, W., Lei, R., Zeng, D., Zhang, Z. (2015). Regularity Guaranteed Human Pose Correction. In: Cremers, D., Reid, I., Saito, H., Yang, MH. (eds) Computer Vision -- ACCV 2014. ACCV 2014. Lecture Notes in Computer Science(), vol 9004. Springer, Cham. https://doi.org/10.1007/978-3-319-16808-1_17

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-16808-1_17

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-16807-4

  • Online ISBN: 978-3-319-16808-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation