Abstract
We propose motion manifold learning and motion primitive segmentation framework for human motion synthesis from motion-captured data. High dimensional motion capture date are represented using a low dimensional representation by topology preserving network, which maps similar motion instances to the neighborhood points on the low dimensional motion manifold. Nonlinear manifold learning between a low dimensional manifold representation and high dimensional motion data provides a generative model to synthesize new motion sequence by controlling trajectory on the low dimensional motion manifold. We segment motion primitives by analyzing low dimensional representation of body poses through motion from motion captured data. Clustering techniques like k-means algorithms are used to find motion primitives after dimensionality reduction. Motion dynamics in training sequences can be described by transition characteristics of motion primitives. The transition matrix represents the temporal dynamics of the motion with Markovian assumption. We can generate new motion sequences by perturbing the temporal dynamics.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Barbic, J., Safonova, A., Pan, J.-Y., Faloutsos, C., Hodgins, J.K., Pollard, N.S.: Segmenting motion capture data into distinct behaviors. In: Proc. of Graphics Interface (2004)
Bettinger, F., Cootes, T.F.: A model of facial behaviour. In: Proc. of FGR, pp. 123–128 (2004)
Bowden, R.: Learning statistical models of human motion. In: Proc. of IEEE Workshop on Human Modeling, Analysis & Synthesis (2000)
Brand, M., Hertzmann, A.: Style machines. In: Proc. of SIGGRAPH, pp. 183–192 (2000)
Brand, M., Kettnaker, V.: Discovery and segmentation of activities in video. IEEE Trans. on PAMIÂ 22(8) (2000)
Elgammal, A., Lee, C.-S.: Separating style and content on a nonlinear manifold. In: Proc. CVPR, vol. 1, pp. 478–485 (2004)
Galata, A., Johnson, N., Hogg, D.: Learning variable-length markov models of behavior. Computer Vision and Image Understanding 81, 398–413 (2001)
Grochow, K., Martin, S.L., Hertzmann, A., Popovic, Z.: Style-based inverse kinematics. ACM Trans. Graph. 23(3), 522–531 (2004)
Kovar, L., Gleicher, M.: Flexible automatic motion blending with registration curves. In: Proc. of SCA, pp. 214–224 (2003)
Mussa-Ivaldi, F., Bizzi, E.: Motor learning through the combination of primitives. Philosopical Transactions of the Royal Society of London Seris B, Biological Science 355, 1755–1769 (2000)
Park, S., Aggarwal, J.K.: Recognition of two-person interactions using a hierarchical bayesian network. In: Proc. of Workshop on Video surveillance, pp. 65–76. ACM Press, New York (2003)
Poggio, T., Girosi, F.: Networks for approximation and learning. Proc. IEEE 78(9), 1481–1497 (1990)
Ritter, H., Martinetz, T., Schulten, K.: Nueral Computation and Self-Organizing Maps. Addison-Wesley, Reading (1991)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lee, CS., Elgammal, A. (2006). Human Motion Synthesis by Motion Manifold Learning and Motion Primitive Segmentation. In: Perales, F.J., Fisher, R.B. (eds) Articulated Motion and Deformable Objects. AMDO 2006. Lecture Notes in Computer Science, vol 4069. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11789239_48
Download citation
DOI: https://doi.org/10.1007/11789239_48
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-36031-5
Online ISBN: 978-3-540-36032-2
eBook Packages: Computer ScienceComputer Science (R0)