×

Generative tracking of 3D human motion by hierarchical annealed genetic algorithm. (English) Zbl 1161.68779

Summary: We present a generative method for reconstructing 3D human motion from single images and monocular image sequences. Inadequate observation information in monocular images and the complicated nature of human motion make the 3D human pose reconstruction challenging. In order to mine more prior knowledge about human motion, we extract the motion subspace by performing conventional principle component analysis on small sample set of motion capture data. In doing so, we also reduce the problem dimensionality so that the generative pose recovering can be performed more effectively. And, the extracted subspace is naturally hierarchical. This allows us to explore the solution space efficiently. We design an Annealed Genetic Algorithm (AGA) and hierarchical annealed genetic algorithm for human motion analysis that searches the optimal solutions by utilizing the hierarchical characteristics of state space. In tracking scenario, we embed the evolutionary mechanism of AGA into the framework of evolution strategy for adapting the local characteristics of fitness function. We adopt the robust shape contexts descriptor to construct the matching function. Our methods are demonstrated in different motion types and different image sequences. Results of human motion estimation show that our novel generative method can achieve viewpoint invariant 3D pose reconstruction.

MSC:

68T10 Pattern recognition, speech recognition
68W05 Nonnumerical algorithms
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] C. Sminchisescu, A. Kanaujia, Z. Li, D. Metaxas, Discriminative density propagation for 3D human motion estimation, in: Proceedings of the Conference on Computer Vision and Pattern Recognition, 2005, pp. 217-323.; C. Sminchisescu, A. Kanaujia, Z. Li, D. Metaxas, Discriminative density propagation for 3D human motion estimation, in: Proceedings of the Conference on Computer Vision and Pattern Recognition, 2005, pp. 217-323.
[2] Agarwal, A.; Triggs, B., Recovering 3D human pose from monocular images, IEEE Trans. Pattern Anal. Mach. Intell., 28, 1, 44-58 (2006)
[3] R. Rosales, S. Sclaroff, Learning body pose via specialized maps, Adv. Neural Inf. Process. Syst;2002.; R. Rosales, S. Sclaroff, Learning body pose via specialized maps, Adv. Neural Inf. Process. Syst;2002.
[4] M. Brand, Shadow puppetry, in: International Conference on Computer Vision, vol. 2, 1999, p. 1237.; M. Brand, Shadow puppetry, in: International Conference on Computer Vision, vol. 2, 1999, p. 1237.
[5] A. Elgammal, C. Lee, Inferring 3D body pose from silhouettes using activity manifold learning, in: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, 2004, CVPR 2004.; A. Elgammal, C. Lee, Inferring 3D body pose from silhouettes using activity manifold learning, in: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, 2004, CVPR 2004.
[6] G. Shakhnarovich, P. Viola, T. Darrell, Fast pose estimation with parameter-sensitive hashing, in: Proceedings of the Ninth IEEE International Conference on Computer Vision, 2003, pp. 750-757.; G. Shakhnarovich, P. Viola, T. Darrell, Fast pose estimation with parameter-sensitive hashing, in: Proceedings of the Ninth IEEE International Conference on Computer Vision, 2003, pp. 750-757.
[7] J. Deutscher, A. Blake, I. Reid, Articulated body motion capture by annealed particle filtering, in: Proceedings of the 2000 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, 2000, pp. 126-133.; J. Deutscher, A. Blake, I. Reid, Articulated body motion capture by annealed particle filtering, in: Proceedings of the 2000 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, 2000, pp. 126-133.
[8] H. Sidenbladh, M. Black, D. Fleet, Stochastic tracking of 3D human figures using 2D image motion, in: European Conference on Computer Vision, vol. 2, 2000, pp. 702-718.; H. Sidenbladh, M. Black, D. Fleet, Stochastic tracking of 3D human figures using 2D image motion, in: European Conference on Computer Vision, vol. 2, 2000, pp. 702-718.
[9] C. Sminchisescu, B. Triggs, Covariance scaled sampling for monocular 3D body tracking, in: IEEE International Conference on Computer Vision and Pattern Recognition, vol. 1, 2001, pp. 447-454.; C. Sminchisescu, B. Triggs, Covariance scaled sampling for monocular 3D body tracking, in: IEEE International Conference on Computer Vision and Pattern Recognition, vol. 1, 2001, pp. 447-454.
[10] Y. Wu, G. Hua, T. Yu, Tracking articulated body by dynamic Markov network, in: Proceedings of the Ninth IEEE International Conference on Computer Vision, 2003, pp. 1094-1101.; Y. Wu, G. Hua, T. Yu, Tracking articulated body by dynamic Markov network, in: Proceedings of the Ninth IEEE International Conference on Computer Vision, 2003, pp. 1094-1101.
[11] Agarwal, A.; Triggs, B., Tracking articulated motion using a mixture of autoregressive models, (Proceedings of the European Conference on Computer Vision, vol. 3023 (2004)), 54-65 · Zbl 1098.68715
[12] Ning, H.; Tan, T.; Wang, L.; Hu, W., People tracking based on motion model and motion constraints with automatic initialization, Pattern Recognition, 37, 7, 1423-1440 (2004)
[13] Mori, G.; Malik, J., Recovering 3D human body configurations using shape contexts, IEEE Trans. Pattern Anal. Mach. Intell., 28, 7, 1052-1062 (2006)
[14] H. Sidenbladh, M. Black, L. Sigal, Implicit probabilistic models of human motion for synthesis and tracking, in: European Conference on Computer Vision, vol. 1, 2002, pp. 784-800.; H. Sidenbladh, M. Black, L. Sigal, Implicit probabilistic models of human motion for synthesis and tracking, in: European Conference on Computer Vision, vol. 1, 2002, pp. 784-800. · Zbl 1034.68668
[15] R. Urtasun, D. Fleet, P. Fua, Monocular 3-D tracking of the golf swing, in: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2.; R. Urtasun, D. Fleet, P. Fua, Monocular 3-D tracking of the golf swing, in: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2.
[16] Michalewicz, Z., Genetic \(\operatorname{Algorithms} + \operatorname{Data} \operatorname{Structures} = \operatorname{Evolution} \operatorname{Programs} (1996)\), Springer: Springer London, UK
[17] Arnold, D.; Beyer, H., Optimum tracking with evolution strategies, Evol. Comput., 14, 3, 291-308 (2006)
[18] Belongie, S.; Malik, J.; Puzicha, J., Shape matching and object recognition using shape contexts, IEEE Trans. Pattern Anal. Mach. Intell., 24, 4, 509-522 (2002)
[19] Aggarwal, J.; Cai, Q., Human motion analysis: a review, Comput. Vision Image Understanding, 73, 3, 428-440 (1999)
[20] Gavrila, D., Visual analysis of human movement: a survey, Comput. Vision Image Understanding, 73, 1, 82-98 (1999) · Zbl 0924.68174
[21] Moeslund, T.; Granum, E., A survey of computer vision-based human motion capture, Comput. Vision Image Understanding, 81, 3, 231-268 (2001) · Zbl 1011.68548
[22] R. Urtasun, P. Fua, 3D human body tracking using deterministic temporal motion models, in: European Conference on Computer Vision, vol. 3, 2004, pp. 92-106.; R. Urtasun, P. Fua, 3D human body tracking using deterministic temporal motion models, in: European Conference on Computer Vision, vol. 3, 2004, pp. 92-106.
[23] Arulampalam, M.; Maskell, S.; Gordon, N.; Clapp, T.; Sci, D.; Organ, T.; Adelaide, S., A tutorial on particle filters for online nonlinear/non-Gaussian-Bayesian tracking, IEEE Trans. Signal Proc., 50, 2, 174-188 (2002)
[24] J. Deutscher, A. Davison, I. Reid, Automatic partitioning of high dimensional search spaces associated with articulated body motion capture, in: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.; J. Deutscher, A. Davison, I. Reid, Automatic partitioning of high dimensional search spaces associated with articulated body motion capture, in: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.
[25] R. Rosales, V. Athitsos, L. Sigal, S. Sclaroff, 3D hand pose reconstruction using specialized mappings, in: IEEE International Conference on Computer Vision, 2001, pp. 378-385.; R. Rosales, V. Athitsos, L. Sigal, S. Sclaroff, 3D hand pose reconstruction using specialized mappings, in: IEEE International Conference on Computer Vision, 2001, pp. 378-385.
[26] C. Taylor, Reconstruction of articulated objects from point correspondences in a single uncalibrated image, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, 2000.; C. Taylor, Reconstruction of articulated objects from point correspondences in a single uncalibrated image, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, 2000. · Zbl 1011.68537
[27] Jin, X.; Tai, C., Convolution surfaces for arcs and quadratic curves with a varying kernel, Visual Comput., 18, 8, 530-546 (2002)
[28] Tong, M.; Liu, Y.; Huang, T. S., 3D human model and joint parameter estimation from monocular image, Pattern Recognition Lett., 28, 7, 797-805 (2007)
[29] L. Sigal, M.J. Black., Humaneva: Synchronized video and motion capture dataset for evaluation of articulated human motion, Technical Report CS-06-08, Brown University.; L. Sigal, M.J. Black., Humaneva: Synchronized video and motion capture dataset for evaluation of articulated human motion, Technical Report CS-06-08, Brown University.
[30] Beyer, H., The Theory of Evolution Strategies (2001), Springer: Springer Berlin · Zbl 1001.68186
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.