Abstract
Reconstructing 3D human poses from a single 2D image is an ill-posed problem without considering the human body model. Explicitly enforcing physiological constraints is known to be non-convex and usually leads to difficulty in finding an optimal solution. An attractive alternative is to learn a prior model of the human body from a set of human pose data. In this paper, we develop a new approach, namely pose locality constrained representation (PLCR), to model the 3D human body and use it to improve 3D human pose reconstruction. In this approach, the human pose space is first hierarchically divided into lower-dimensional pose subspaces by subspace clustering. After that, a block-structural pose dictionary is constructed by concatenating the basis poses from all the pose subspaces. Finally, PLCR utilizes the block-structural pose dictionary to explicitly encourage pose locality in human-body modeling – nonzero coefficients are only assigned to the basis poses from a small number of pose subspaces that are close to each other in the pose-subspace hierarchy. We combine PLCR into the matching-pursuit based 3D human-pose reconstruction algorithm and show that the proposed PLCR-based algorithm outperforms the state-of-the-art algorithm that uses the standard sparse representation and physiological regularity in reconstructing a variety of human poses from both synthetic data and real images.
Chapter PDF
Similar content being viewed by others
References
Di Franco, D.E., Cham, T.J., Rehg, J.M.: Reconstruction of 3D figure motion from 2D correspondences. In: CVPR (2001)
Elhamifar, E., Vidal, R.: Sparse subspace clustering. In: CVPR (2009)
Jenatton, R., Mairal, J., Obozinski, G., Bach, F.: Proximal methods for hierarchical sparse coding. The Journal of Machine Learning Research 12, 2297–2334 (2011)
Lee, H.J., Chen, Z.: Determination of 3D human body postures from a single view. Computer Vision, Graphics, and Image Processing 30(2), 148–168 (1985)
Li, R., Tian, T.P., Sclaroff, S., Yang, M.H.: 3D human motion tracking with a coordinated mixture of factor analyzers. IJCV 87(1-2), 170–190 (2010)
Liebowitz, D., Carlsson, S.: Uncalibrated motion capture exploiting articulated structure constraints. IJCV 51(3), 171–187 (2003)
Liu, G., Lin, Z., Yan, S., Sun, J., Yu, Y., Ma, Y.: Robust recovery of subspace structures by low-rank representation. TPAMI 35(1), 171–184 (2013)
Liu, G., Lin, Z., Yu, Y.: Robust subspace segmentation by low-rank representation. In: ICML (2010)
Parameswaran, V., Chellappa, R.: View independent human body pose estimation from a single perspective image. In: CVPR (2004)
Raja, K., Laptev, I., Pérez, P., Oisel, L.: Joint pose estimation and action recognition in image graphs. In: ICIP (2011)
Ramakrishna, V., Kanade, T., Sheikh, Y.: Reconstructing 3D human pose from 2D image landmarks. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part IV. LNCS, vol. 7575, pp. 573–586. Springer, Heidelberg (2012)
Safonova, A., Hodgins, J.K., Pollard, N.S.: Synthesizing physically realistic human motion in low-dimensional, behavior-specific spaces. TOG 23(3), 514–521 (2004)
Salzmann, M., Urtasun, R.: Implicitly constrained gaussian process regression for monocular non-rigid pose estimation. In: NIPS (2010)
Shi, J., Malik, J.: Normalized cuts and image segmentation. TPAMI, 888–905 (2000)
Soltanolkotabi, M., Elhamifar, E., Candes, E.: Robust subspace clustering. arXiv preprint arXiv:1301.2603 (2013)
Taylor, C.J.: Reconstruction of articulated objects from point correspondences in a single uncalibrated image. In: CVPR (2000)
Valmadre, J., Lucey, S.: Deterministic 3D human pose estimation using rigid structure. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part III. LNCS, vol. 6313, pp. 467–480. Springer, Heidelberg (2010)
Vidal, R.: Subspace clustering. Signal Processing Magazine 28(2), 52–68 (2011)
Wang, J., Yang, J., Yu, K., Lv, F., Huang, T., Gong, Y.: Locality-constrained linear coding for image classification. In: CVPR, pp. 3360–3367 (2010)
Wei, X.K., Chai, J.: Modeling 3D human poses from uncalibrated monocular images. In: ICCV (2009)
Yang, A.Y., Iyengar, S., Sastry, S., Bajcsy, R., Kuryloski, P., Jafari, R.: Distributed segmentation and classification of human actions using a wearable motion sensor network. In: CVPRW (2008)
Yao, A., Gall, J., Van Gool, L.: Coupled action recognition and pose estimation from multiple views. IJCV (2012)
Yu, T.H., Kim, T.K., Cipolla, R.: Unconstrained monocular 3D human pose estimation by action detection and cross-modality regression forest. In: CVPR (2013)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Fan, X., Zheng, K., Zhou, Y., Wang, S. (2014). Pose Locality Constrained Representation for 3D Human Pose Reconstruction. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds) Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol 8689. Springer, Cham. https://doi.org/10.1007/978-3-319-10590-1_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-10590-1_12
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10589-5
Online ISBN: 978-3-319-10590-1
eBook Packages: Computer ScienceComputer Science (R0)