Skip to main content
SpringerLink
Log in

3D human pose estimation from image using couple sparse coding

  • Original Paper
  • Published:
Machine Vision and Applications Aims and scope Submit manuscript

Abstract

Recent studies have demonstrated that high-level semantics in data can be captured using sparse representation. In this paper, we propose an approach to human body pose estimation in static images based on sparse representation. Given a visual input, the objective is to estimate 3D human body pose using feature space information and geometrical information of the pose space. On the assumption that each data point and its neighbors are likely to reside on a locally linear patch of the underlying manifold, our method learns the sparse representation of the new input using both feature and pose space information and then estimates the corresponding 3D pose by a linear combination of the bases of the pose dictionary. Two strategies for dictionary construction are presented: (i) constructing the dictionary by randomly selecting the frames of a sequence and (ii) selecting specific frames of a sequence as dictionary atoms. We analyzed the effect of each strategy on the accuracy of pose estimation. Extensive experiments on datasets of various human activities show that our proposed method outperforms state-of-the-art methods.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Notes

  1. BVH format created by Biovision Company to describing 3D pose in animation production. http://www.cs.wisc.edu/graphics/Courses/cs-838-1999/Jeff/BVH.html

  2. http://www.poser.com

References

  1. Cmu graphics lab motion capture database (2013). http://mocap.cs.cmu.edu

  2. Agarwal, A., Triggs, B.: Monocular human motion capture with a mixture of regressors. In: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition—Workshops, vol. 03, CVPR ’05, pp. 72. IEEE Computer Society, Washington, DC (2005) doi:10.1109/CVPR.2005.496

  3. Agarwal, A., Triggs, B.: Recovering 3d human pose from monocular images. IEEE Trans. Pattern Anal. Mach. Intell. 28(1), 44–58 (2006). doi:10.1109/TPAMI.2006.21

    Article  Google Scholar 

  4. Aharon, M., Elad, M., Bruckstein, A.: K-svd: An algorithm for designing overcomplete dictionaries for sparse representation. Trans. Sig. Proc. 54(11), 4311–4322 (2006). doi:10.1109/TSP.2006.881199

    Article  Google Scholar 

  5. Andriluka, M., Roth, S., Schiele, B.: Monocular 3d pose estimation and tracking by detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 623–630 (2010). doi:10.1109/CVPR.2010.5540156

  6. Bo, L., Sminchisescu, C.: Twin gaussian processes for structured prediction. Int. J. Comput. Vision 87(1–2), 28–52 (2010). doi:10.1007/s11263-008-0204-y

    Article  Google Scholar 

  7. Cai, T.T., Wang, L.: Orthogonal matching pursuit for sparse signal recovery with noise. IEEE Trans. Inf. Theor. 57(7), 4680–4688 (2011). doi:10.1109/TIT.2011.2146090

    Article  MathSciNet  Google Scholar 

  8. Candes, E.J., Tao, T.: Near-optimal signal recovery from random projections: universal encoding strategies? IEEE Trans. Inf. Theor. 52(12), 5406–5425 (2006). doi:10.1109/TIT.2006.885507

    Article  MathSciNet  Google Scholar 

  9. Chen, C., Yang, Y., Nie, F., Odobez, J.M.: 3d human pose recovery from image by efficient visual feature selection. Comput. Vis. Image Underst. 115(3), 290–299 (2011). doi:10.1016/j.cviu.2010.11.007

    Article  Google Scholar 

  10. Chen, S.S., Donoho, D.L., Saunders, M.A.: Atomic decomposition by basis pursuit. SIAM Rev. 43(1), 129–159 (2001). doi:10.1137/S003614450037906X

    Article  MATH  MathSciNet  Google Scholar 

  11. Christoudias, C.M., Darrell, T.: On modelling nonlinear shape-and-texture appearance manifolds. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, vol. 02, CVPR ’05, pp. 1067–1074. IEEE Computer Society, Washington, DC (2005). doi:10.1109/CVPR.2005.255

  12. Donoho, D.L.: Compressed sensing. IEEE Trans. Inf. Theor. 52(4), 1289–1306 (2006). doi:10.1109/TIT.2006.871582

    Article  MATH  MathSciNet  Google Scholar 

  13. Donoho, D.L.: For most large underdetermined systems of linear equations the minimal l1-norm solution is also the sparsest solution. Commun. Pure Appl. Math. 59(6), 797–829 (2006)

    Article  MATH  MathSciNet  Google Scholar 

  14. Efron, B., Hastie, T., Johnstone, I., Tibshirani, R.: Least angle regression. Ann. Stat. 32, 407–499 (2004)

    Article  MATH  MathSciNet  Google Scholar 

  15. Elgammal, A., Lee, C.S.: Inferring 3d body pose from silhouettes using activity manifold learning. In: Proceedings of the IEEE Computer Society Conference on Computer vision and Pattern Recognition. CVPR’04, pp. 681–688. IEEE Computer Society, Washington, DC (2004)

  16. Hara, K., Kurokawa, T.: Human pose estimation using patch-based candidate generation and model-based verification. In: IEEE International Conference on Automatic Face Gesture Recognition and Workshops (FG), pp. 687–693 (2011). doi:10.1109/FG.2011.5771331

  17. Huang, J.B., Yang, M.H.: Estimating human pose from occluded images. In: ACCV (1), Lecture Notes in Computer Science, vol. 5994, pp. 48–60. Springer, Berlin (2009)

  18. Huang, J.B., Yang, M.H.: Fast sparse representation with prototypes. In: CVPR, pp. 3618–3625. IEEE, New York (2010)

  19. Jiang, H.: 20th International Conference on 3d human pose reconstruction using millions of exemplars. In: Pattern Recognition (ICPR), pp. 1674–1677 (2010). doi:10.1109/ICPR.2010.414

  20. Lee, C.S., Elgammal, A.M.: Modeling view and posture manifolds for tracking. In: ICCV, pp. 1–8. IEEE, New York (2007)

  21. Lee, H., Battle, A., Raina, R., Ng, A.Y.: Efficient sparse coding algorithms. In: NIPS, pp. 801–808. NIPS, Kolkata (2007)

  22. Lee, M.W., Nevatia, R.: Human pose tracking in monocular sequence using multilevel structured models. IEEE Trans. Pattern Anal. Mach. Intell. 31(1), 27–38 (2009). doi:10.1109/TPAMI.2008.35.

  23. Mairal, J., Bach, F., Ponce, J.: Task-driven dictionary learning. IEEE Trans. Pattern Anal. Mach. Intell. 34(4), 791–804 (2012). doi:10.1109/TPAMI.2011.156

    Article  Google Scholar 

  24. Mori, G., Malik, J.: Recovering 3d human body configurations using shape contexts. IEEE Trans. Pattern Anal. Mach. Intell. 28(7), 1052–1062 (2006)

    Article  Google Scholar 

  25. Olshausen, B.A., Field, D.J.: Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381, 607–609 (1996)

    Article  Google Scholar 

  26. Olshausen, B.A., Field, D.J.: Sparse coding with an overcomplete basis set: a strategy employed by v1? Vision Res. 37, 3311–3325 (1997)

    Article  Google Scholar 

  27. Pourdamghani, N., Rabiee, H.R., Faghri, F., Rohban, M.H.: Graph based semi-supervised human pose estimation: When the output space comes to help. Pattern Recogn. Lett. 33(12), 1529–1535 (2012). doi:10.1016/j.patrec.2012.04.012

    Article  Google Scholar 

  28. Rao, R.P.N., Olshausen, B.A., Lewicki, M.S.: Probabilistic models of the brain: perception and neural function. MIT Press, Cambridge (2002)

    Google Scholar 

  29. Rubinstein, R., Bruckstein, A., Elad, M.: Dictionaries for sparse representation modeling. Proc. IEEE 98(6), 1045–1057 (2010). doi:10.1109/JPROC.2010.2040551

    Article  Google Scholar 

  30. Serre, T.: Learning a dictionary of shape-components in visual cortex: comparison with neurons, humans and machines. Mass. Inst. Technol. (2006)

  31. Shakhnarovich, G., Viola, P., Darrell, T.: Fast pose estimation with parameter-sensitive hashing. In: Proceedings of the Ninth IEEE International Conference on Computer Vision, vol. 2, ICCV ’03, pp. 750. IEEE Computer Society, Washington, DC (2003)

  32. Shang, L., Zhou, Y., Tao, L., Sun, Z.l.: Super-resolution restoration of mmw image using sparse representation based on couple dictionaries. In: Emerging Intelligent Computing Technology and Applications, pp. 286–291. Springer, Berlin (2012)

  33. Tzimiropoulos, G., Zafeiriou, S., Pantic, M.: Sparse representations of image gradient orientations for visual recognition and tracking. In: Proceedings of IEEE International Conference Computer Vision and Pattern Recognition (CVPR-W11), Workshop on CVPR for Human Behaviour Analysis, pp. 26–33. Colorado Springs, USA (2011)

  34. Urtasun, R., Fleet, D.J., Hertzmann, A., Fua, P.: Priors for people tracking from small training sets. In: Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV) vol. 1, vol. 01, ICCV ’05, pp. 403–410. IEEE Computer Society, Washington, DC (2005) doi:10.1109/ICCV.2005.193

  35. Wright, J., Ma, Y., Mairal, J., Sapiro, G., Huang, T., Yan, S.: Sparse representation for computer vision and pattern recognition (2009)

  36. Wright, J., Yang, A.Y., Ganesh, A., Sastry, S.S., Ma, Y.: Robust face recognition via sparse representation. IEEE Trans. Pattern Anal. Mach. Intell. 31(2), 210–227 (2009). doi:10.1109/TPAMI.2008.79

  37. Yang, J., Wang, Z., Lin, Z., Cohen, S., Huang, T.: Coupled dictionary training for image super-resolution. IEEE Trans. Image Process. 21(8), 3467–3478 (2012)

    Article  MathSciNet  Google Scholar 

  38. Yang, S., Liu, Z., Wang, M., Sun, F., Jiao, L.: Multitask dictionary learning and sparse representation based single-image super-resolution reconstruction. Neurocomputing 74(17), 3193–3203 (2011). doi:10.1016/j.neucom.2011.04.014

    Article  Google Scholar 

  39. Zheng, M., Bu, J., Chen, C., Wang, C., Zhang, L., Qiu, G., Cai, D.: Graph regularized sparse coding for image representation. Trans. Image Proc. 20(5), 1327–1336 (2011). doi:10.1109/TIP.2010.2090535

    Article  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Sharif University of Technology, Tehran, Iran

    Mohammadreza Zolfaghari, Amin Jourabloo, Bahman Pedrood & Mohammad T. Manzuri-Shalmani

  2. Amirkabir University of Technology, Tehran, Iran

    Samira Ghareh Gozlou

Authors
  1. Mohammadreza Zolfaghari
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Amin Jourabloo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Samira Ghareh Gozlou
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Bahman Pedrood
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Mohammad T. Manzuri-Shalmani
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mohammadreza Zolfaghari.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zolfaghari, M., Jourabloo, A., Gozlou, S.G. et al. 3D human pose estimation from image using couple sparse coding. Machine Vision and Applications 25, 1489–1499 (2014). https://doi.org/10.1007/s00138-014-0613-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00138-014-0613-6

Keywords

Search

Navigation