The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.09 - September (2011 vol.33)
pp: 1911-1918
Hao Jiang , Boston College, Chestnut Hill
ABSTRACT
A novel consistent max-covering method is proposed for human pose estimation. We focus on problems in which a rough foreground estimation is available. Pose estimation is formulated as a jigsaw puzzle problem in which the body part tiles maximally cover the foreground region, match local image features, and satisfy body plan and color constraints. This method explicitly imposes a global shape constraint on the body part assembly. It anchors multiple body parts simultaneously and introduces hyperedges in the part relation graph, which is essential for detecting complex poses. Using multiple cues in pose estimation, our method is resistant to cluttered foregrounds. We propose an efficient linear method to solve the consistent max-covering problem. A two-stage relaxation finds the solution in polynomial time. Our experiments on a variety of images and videos show that the proposed method is more robust than previous locally constrained methods.
INDEX TERMS
Human pose estimation, consistent max covering, linear programming.
CITATION
Hao Jiang, "Human Pose Estimation Using Consistent Max Covering", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.33, no. 9, pp. 1911-1918, September 2011, doi:10.1109/TPAMI.2011.92
REFERENCES
[1] X. Bai and W.Y. Liu, "Skeleton Pruning by Contour Partitioning with Discrete Curve Evolution," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no. 3, pp. 449-462, Mar. 2007.
[2] R. Rosales and S. Sclaroff, "Inferring Body Pose without Tracking Body Parts," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2000.
[3] A. Agarwal and B. Triggs, "3D Human Pose from Silhouettes by Relevance Vector Regression," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2004.
[4] K. Grauman, G. Shakhnarovich, and T. Darrell, "Inferring 3D Structure with a Statistical Image-Based Shape Model," Proc. IEEE Ninth Int'l Conf. Computer Vision, 2003.
[5] A. Elgammal and C.S. Lee, "Inferring 3D Body Pose from Silhouettes Using Activity Manifold Learning," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2004.
[6] J.M. Wang, D.J. Fleet, and A. Hertzmann, "Gaussian Process Dynamical Models for Human Motion," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 30, no. 2, pp. 283-298, Feb. 2008.
[7] G. Mori and J. Malik, "Estimating Human Body Configurations Using Shape Context Matching," Proc. Seventh European Conf. Computer Vision, 2002.
[8] D.M. Gavrila, "A Bayesian, Exemplar-Based Approach to Hierarchical Shape Matching," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no. 8, pp. 1408-1421, Aug. 2007.
[9] G. Shakhnarovich, P. Viola, and T. Darrell, "Fast Pose Estimation with Parameter Sensitive Hashing," Proc. IEEE Ninth Int'l Conf. Computer Vision, 2003.
[10] P.F. Felzenszwalb and D.P. Huttenlocher, "Pictorial Structures for Object Recognition," Int'l J. Computer Vision, vol. 61, no. 1, 2005.
[11] S. Ioffe and D.A. Forsyth, "Probabilistic Methods for Finding People," Int'l J. Computer Vision, vol. 43, no. 1, June 2001.
[12] M.W. Lee and I. Cohen, "Proposal Maps Driven MCMC for Estimating Human Body Pose in Static Images," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2004.
[13] X. Ren, A. Berg, and J. Malik, "Recovering Human Body Configurations Using Pairwise Constraints between Parts," Proc. IEEE 10th Int'l Conf. Computer Vision, 2005.
[14] D. Ramanan, "Learning to Parse Images of Articulated Objects," Neural Information Processing Systems, 2006.
[15] H. Jiang and D.R. Martin, "Global Pose Estimation Using Non-Tree Models," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2008.
[16] L. Sigal and M.J. Black, "Measure Locally, Reasoning Globally: Occlusion-Sensitive Articulated Pose Estimation," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2006.
[17] V. Chvátal, Linear Programming. W.H. Freeman and Company, 1983.
[18] H. Ning, W. Xu, Y. Gong, and T.S. Huang, "Discriminative Learning of Visual Words for 3D Human Pose Estimation," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2008.
[19] T. Tian and S. Sclaroff, "Fast Globally Optimal 2D Human Detection with Loopy Graph Models," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2010.
[20] V. Ferrari, M.M. Jimenez, and A. Zisserman, "Pose Search: Retrieving People Using Their Pose," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2010.
[21] S. Johnson and M. Everingham, "Combining Discriminative Appearance and Segmentation Cues for Articulated Human Pose Estimation," Proc. IEEE Int'l Workshop Machine Learning for Vision-Based Motion Analysis, 2009.
[22] M. Andriluka, S. Roth, and B. Schiele, "Pictorial Structures Revisited: People Detection and Articulated Pose Estimation," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2009.
[23] H. Jiang, "Human Pose Estimation Using Consistent Max-Covering," Proc. IEEE 12th Int'l Conf. Computer Vision, 2009.
[24] HumanEva Data Set, http://vision.cs.brown.eduhumaneva, 2011.
[25] libDAI, http://people.kyb.tuebingen.mpg.de/jorism libDAI, 2011.
[26] B. Sapp, C. Jordan, and B. Taskar, "Adaptive Pose Priors for Pictorial Structures," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2010.
19 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool