Abstract
We address the problem of recovering 3D human pose from single 2D images, in which the pose estimation problem is formulated as a direct nonlinear regression from image observation to 3D joint positions. One key issue that has not been addressed in the literature is how to estimate 3D pose when humans in the scenes are partially or heavily occluded. When occlusions occur, features extracted from image observations (e.g., silhouettes-based shape features, histogram of oriented gradient, etc.) are seriously corrupted, and consequently the regressor (trained on un-occluded images) is unable to estimate pose states correctly. In this paper, we present a method that is capable of handling occlusions using sparse signal representations, in which each test sample is represented as a compact linear combination of training samples. The sparsest solution can then be efficiently obtained by solving a convex optimization problem with certain norms (such as l 1-norm). The corrupted test image can be recovered with a sparse linear combination of un-occluded training images which can then be used for estimating human pose correctly (as if no occlusions exist). We also show that the proposed approach implicitly performs relevant feature selection with un-occluded test images. Experimental results on synthetic and real data sets bear out our theory that with sparse representation 3D human pose can be robustly estimated when humans are partially or heavily occluded in the scenes.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Sigal, L., Isard, M., Sigelman, B., Black, M.: Attractive people: Assembling loose-limbed models using non-parametric belief propagation. In: NIPS, pp. 1539–1546 (2004)
Grauman, K., Shakhnarovich, G., Darrell, T.: Inferring 3d structure with a statistical image-based shape model. In: ICCV, pp. 641–647 (2003)
Sminchisescu, C., Kanaujia, A., Li, Z., Metaxas, D.: Discriminative density propagation for 3d human motion estimation. In: CVPR, pp. 390–397 (2005)
Sigal, L., Black, M.: Predicting 3d people from 2d pictures. In: Perales, F.J., Fisher, R.B. (eds.) AMDO 2006. LNCS, vol. 4069, pp. 185–195. Springer, Heidelberg (2006)
Bo, L., Sminchisescu, C., Kanaujia, A., Metaxas, D.: Fast algorithms for large scale conditional 3d prediction. In: CVPR (2008)
Agarwal, A., Triggs, B.: A local basis representation for estimating human pose from cluttered images. In: Narayanan, P.J., Nayar, S.K., Shum, H.-Y. (eds.) ACCV 2006. LNCS, vol. 3851, pp. 50–59. Springer, Heidelberg (2006)
Elgammal, A., Lee, C.: Inferring 3d body pose from silhouettes using activity manifold learning. In: CVPR, vol. 2, pp. 681–688 (2004)
Jaeggli, T., Koller-Meier, E., Gool, L.V.: Learning generative models for multi-activity body pose estimation. IJCV 83(2), 121–134 (2009)
Sminchisescu, C., Kanaujia, A., Metaxas, D.: Bm 3 e: Discriminative density propagation for visual tracking. PAMI 29(11), 2030–2044 (2007)
Bissacco, A., Yang, M.H., Soatto, S.: Fast human pose estimation using appearance and motion via multi-dimensional boosting regression. In: CVPR, pp. 1–8 (2007)
Poppe, R.: Evaluating example-based pose estimation: experiments on the HumanEva sets. In: IEEE Workshop on Evaluation of Articulated Human Motion and Pose Estimation (2007)
Okada, R., Soatto, S.: Relevant Feature Selection for Human Pose Estimation and Localization in Cluttered Images. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 434–445. Springer, Heidelberg (2008)
Ning, H., Xu, W., Gong, Y., Huang, T.: Discriminative learning of visual words for 3d human pose estimation. In: CVPR (2008)
Moeslund, T., Granum, E.: A survey of computer vision-based human motion capture. Computer Vision and Image Understanding 81(3), 231–268 (2001)
Gavrila, D.: The visual analysis of human movement: A survey. Computer Vision and Image Understanding 73(1), 82–98 (1999)
Fischler, M.A., Elschlager, R.A.: The representation and matching of pictorial structures. IEEE Transactions on Computers 22(1), 67–92 (1973)
Felzenszwalb, P., Huttenlocher, D.: Efficient matching of pictorial structures. In: CVPR, vol. 2, pp. 2066–2073 (2000)
Ronfard, R., Schmid, C., Triggs, B.: Learning to parse pictures of people. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part IV. LNCS, vol. 2353, pp. 700–714. Springer, Heidelberg (2002)
Ioffe, S., Forsyth, D.: Probabilistic methods for finding people. IJCV 43(1), 45–68 (2001)
Ramanan, D., Forsyth, D.: Finding and tracking people from the bottom up. In: CVPR, vol. 2, pp. 467–474 (2003)
Mori, G., Ren, X., Efros, A., Malik, J.: Recovering human body configurations: Combining segmentation and recognition. In: CVPR, vol. 2, pp. 326–333 (2004)
Taylor, C.J.: Reconstruction of articulated objects from point correspondence using a single uncalibrated image. In: CVPR, vol. 1, pp. 667–684 (2000)
Mori, G., Malik, J.: Estimating human body configurations using shape context matching. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part III. LNCS, vol. 2352, pp. 666–680. Springer, Heidelberg (2002)
Brand, M.: Shadow puppetry. In: ICCV, pp. 1237–1244 (1999)
Tipping, M.: Sparse Bayesian learning and the relevance vector machine. Journal of Machine Learning Research 1, 211–244 (2004)
Agarwal, A., Triggs, B.: Recovering 3d human pose from monocular images. PAMI 28(1), 44–58 (2006)
Rosales, R., Sclaroff, S.: Learning body pose via specialized maps. In: NIPS, pp. 1263–1270 (2001)
Shakhnarovich, G., Viola, P., Darrell, T.: Fast pose estimation with parameter-sensitive hashing. In: ICCV, pp. 750–757 (2003)
Candes, E., Romberg, J., Tao, T.: Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information. IEEE Transactions on Information Theory 52(2), 489–509 (2006)
Candes, E., Tao, T.: Near-optimal signal recovery from random projections: Universal encoding strategies? IEEE Transactions on Information Theory 52(12), 5406–5425 (2006)
Donoho, D.: Compressed sensing. IEEE Transactions on Information Theory 52(4), 1289–1306 (2006)
Wright, J., Yang, A., Ganesh, A., Sastry, S., Ma, Y.: Robust face recognition via sparse representation. PAMI 31(2), 210–227 (2009)
Boyd, S.P., Vandenberghe, L.: Convex optimization. Cambridge University Press, Cambridge (2004)
Chen, S., Donoho, D., Saunders, M.: Automatic decomposition by basis pursuit. SIAM Journal of Scientific Computation 20(1), 33–61 (1998)
Rasmussen, C.E., Williams, C.K.I.: Gaussian processes for machine learning. MIT Press, Cambridge (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Huang, JB., Yang, MH. (2010). Estimating Human Pose from Occluded Images. In: Zha, H., Taniguchi, Ri., Maybank, S. (eds) Computer Vision – ACCV 2009. ACCV 2009. Lecture Notes in Computer Science, vol 5994. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-12307-8_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-12307-8_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-12306-1
Online ISBN: 978-3-642-12307-8
eBook Packages: Computer ScienceComputer Science (R0)