Abstract
Estimating human pose in static images is challenging due to the high dimensional state space, presence of image clutter and ambiguities of image observations. We present an MCMC framework for estimating 3D human upper body pose. A generative model, comprising of the human articulated structure, shape and clothing models, is used to formulate likelihood measures for evaluating solution candidates. We adopt a data-driven proposal mechanism for searching the solution space efficiently. We introduce the use of proposal maps, which is an efficient way of implementing inference proposals derived from multiple types of image cues. Qualitative and quantitative results show that the technique is effective in estimating 3D body pose over a variety of images.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Barron, C., Kakadiaris, I.A.: Estimating anthropometry and pose from a single image. In: CVPR 2000, vol. 1, pp. 669–676 (2000)
Bregler, C., Malik, J.: Tracking people with twists and exponential maps. In: CVPR 1998, pp. 8–15 (1998)
Deutscher, J., Davison, A., Reid, I.: Automatic partitioning of high dimensional search spaces associated with articulated body motion capture. In: CVPR 2001, vol. 2, pp. 669–676 (2001)
Ioffe, S., Forsyth, D.A.: Probabilistic methods for finding people. IJCV 43(1), 45–68 (2001)
Lee, M.W., Cohen, I.: Human Body Tracking with Auxiliary Measurements. In: AMFG 2003, pp. 112–119 (2003)
Mori, G., Malik, J.: Estimating Human Body Configurations using Shape Context Matching. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 666–680. Springer, Heidelberg (2002)
Ronfard, R., Schmid, C., Triggs, B.: Learning to parse pictures of people. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 700–714. Springer, Heidelberg (2002)
Rosales, R., Sclaroff, S.: Inferring body pose without tracking body parts. In: CVPR 2000, vol. 2, pp. 721–727 (2000)
Sminchisescu, C., Triggs, B.: Covariance Scaled Sampling for Monocular 3D Body Tracking. In: CVPR 2001, vol. 1, pp. 447–454 (2001)
Sminchisescu, C., Triggs, B.: Kinematic Jump Processes for Monocular Human Tracking. In: CVPR 2003, vol. 1, pp. 69–76 (2003)
Taylor, C.J.: Reconstruction of articulated objects from point correspondences in a single uncalibrated image. CVIU 80(3), 349–363 (2000)
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: CVPR 2001, vol. 1, pp. 511–518 (2001)
Zhu, S., Zhang, R., Tu, Z.: Integrating bottom-up/top-down for object recognition by data driven Markov chain Monte Carlo. In: CVPR 2000, vol. 1, pp. 738–745 (2000)
Zhao, T., Nevatia, R.: Bayesian Human Segmentation in Crowded Situations. In: CVPR 2003, vol. 2, pp. 459–466 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lee, M.W., Cohen, I. (2004). Human Upper Body Pose Estimation in Static Images. In: Pajdla, T., Matas, J. (eds) Computer Vision - ECCV 2004. ECCV 2004. Lecture Notes in Computer Science, vol 3022. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24671-8_10
Download citation
DOI: https://doi.org/10.1007/978-3-540-24671-8_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21983-5
Online ISBN: 978-3-540-24671-8
eBook Packages: Springer Book Archive