Abstract
We propose a novel method to detect human poses in videos by concurrently optimizing body part matching and object segmentation. With a single exemplar image, the proposed method detects the poses of a specific human subject in long video sequences. Matching and segmentation support each other and therefore the simultaneous optimization enables more reliable results. However, efficient concurrent optimization is a great challenge due to its huge search space. We propose an efficient linear method that solves the problem. In this method, the optimal body part matching conforms to local appearances and a human body plan, and the body part configuration is consistent with the object foreground estimated by simultaneous superpixel labeling. Our experiments on a variety of videos show that the proposed method is efficient and more reliable than previous locally constrained approaches.
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.
Similar content being viewed by others
References
Bregler, C., Malik, J., Pullen, K.: Twist based acquisition and tracking of animal and human kinematics. IJCV 56(3), 179–194 (2004)
Sminchisescu, C., Triggs, B.: Estimating articulated human motion with covariance scaled sampling. Inter. J. of Robotics Research 22(6), 371–391 (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)
Gavrila, D.M.: A Bayesian, exemplar-based approach to hierarchical shape matching. TPAMI 29(8) (2007)
Shakhnarovich, G., Viola, P., Darrell, T.: Fast pose estimation with parameter sensitive hashing. In: ICCV 2003 (2003)
Toyama, K., Blake, A.: Probabilistic tracking with exemplars in a metric space. IJCV 48(1), 9–19 (2002)
Ramanan, D., Forsyth, D.A., Zisserman, A.: Strike a pose: tracking people by finding stylized poses. In: CVPR 2005 (2005)
Jiang, H.: Human pose estimation using consistent max-covering. In: ICCV 2009 (2009)
Felzenszwalb, P.F., Huttenlocher, D.P.: Pictorial structures for object recognition. IJCV 61(1) (January 2005)
Ioffe, S., Forsyth, D.A.: Probabilistic methods for finding people. IJCV 43(1), 45–68 (2001)
Ren, X.F., Berg, A.C., Malik, J.: Recovering human body configurations using pairwise constraints between parts. In: ICCV 2005, vol. 1, pp. 824–831 (2005)
Lee, M.W., Cohen, I.: Human upper body pose estimation in static images. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3022, pp. 126–138. Springer, Heidelberg (2004)
Rosales, R., Sclaroff, S.: Inferring body pose without tracking body parts. In: CVPR 2000 (2000)
Sigal, L., Black, M.J.: Measure locally, reason globally: occlusion sensitive articulated pose estimation. In: CVPR 2006 (2006)
Jiang, H., Martin, D.R.: Global pose estimation using non-tree models. In: CVPR 2008 (2008)
Wang, Y., Mori, G.: Multiple tree models for occlusion and spatial constraints in human pose estimation. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 710–724. Springer, Heidelberg (2008)
Mori, G.: Guiding model search using segmentation. In: ICCV 2005 (2005)
Kohli, P., Rihan, J., Bray, M., Torr, P.H.S.: Simultaneous segmentation and pose estimation of humans using dynamic graph Cuts. IJCV 79(3), 285–298 (2008)
Pawan Kumar, M., Torr, P.H.S., Zisserman, A.: OBJCUT. In: CVPR 2005 (2005)
Ramanan, D.: Learning to parse images of articulated objects. In: NIPS 2006 (2006)
Ferrari, V., Manuel, M., Zisserman, A.: Pose search: retrieving people using their pose. In: CVPR 2008 (2008)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. IJCV 59(2) (2004)
Gupta, A., Mittal, A., Davis, L.S.: Constraint integration for efficient multiview pose estimation with self-occlusions. IEEE TPAMI 30(3), 493–506 (2008)
Urtasun, R., Fleet, D., Fua, P.: Temporal motion models for monocular and multiview 3D human body tracking. CVIU 104(2), 157–177 (2006)
Yezzi, A., Zollei, L., Kapur, T.: A variational framework for joint segmentation and registration. In: IEEE Workshop on Mathematical Methods in Biomedical Image Analysis 2001 (2001)
Chen, C., Fan, G.: Hybrid body representation for integrated pose recognition, localization and segmentation. In: CVPR 2008 (2008)
Johnson, S., Everingham, M.: Combining discriminative appearance and segmentation cues for articulated human pose estimation. In: IEEE International Workshop on Machine Learning for Vision-based Motion Analysis (2009)
Andriluka, M., Roth, S., Schiele, B.: Pictorial structures revisited: people detection and articulated pose estimation. In: CVPR 2009 (2009)
Tian, T.P., Sclaroff, S.: Fast globally optimal 2D human detection with loopy graph models. In: CVPR 2010 (2010)
HumanEva Dataset, http://vision.cs.brown.edu/humaneva
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jiang, H. (2011). Finding Human Poses in Videos Using Concurrent Matching and Segmentation. In: Kimmel, R., Klette, R., Sugimoto, A. (eds) Computer Vision – ACCV 2010. ACCV 2010. Lecture Notes in Computer Science, vol 6492. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19315-6_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-19315-6_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19314-9
Online ISBN: 978-3-642-19315-6
eBook Packages: Computer ScienceComputer Science (R0)