Abstract
If we consider the appearance of human motion such as gait, facial expression and gesturing, most of such activities result in nonlinear manifolds in the image space. Although the intrinsic body configuration manifolds might be very low in dimensionality, the resulting appearance manifold is challenging to model given various aspects that affects the appearance such as the view point, the person shape and appearance, etc. In this paper we learn decomposable generative models that explicitly decompose the intrinsic body configuration as a function of time from other conceptually orthogonal aspects that affects the appearance such as the view point, the person performing the action, etc. The frameworks is based on learning nonlinear mappings from a conceptual representation of the motion manifold that is homeomorphic to the actual manifold and decompose other sources of variation in the mapping coefficient space.
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
Agarwal, A., Triggs, B.: 3d human pose from silhuettes by relevance vector regression. In: Proc. CVPR, vol. 2, pp. 882–888 (2004)
Belhumeur, P.N., Hespanha, J., Kriegman, D.J.: Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. In: Buxton, B.F., Cipolla, R. (eds.) ECCV 1996. LNCS, vol. 1064, pp. 45–58. Springer, Heidelberg (1996)
Brand, M.: Shadow puppetry. In: Proc. ICCV, pp. 1237–1244 (1999)
Brand, M., Huang, K.: A unifying theorem for spectral embedding and clustering. In: Proc. of the Ninth International Workshop on AI and Statistics (2003)
Bregler, C., Omohundro, S.M.: Nonlinear manifold learning for visual speech recognition. In: Proc. ICCV, pp. 494–499 (1995)
Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J.: Active shape models: Their training and application. CVIU 61(1), 38–59 (1995)
Elgammal, A., Lee, C.-S.: Inferring 3d body pose from silhouettes using activity manifold learning. In: Proc. CVPR, vol. 2, pp. 681–688 (2004)
Elgammal, A., Lee, C.-S.: Separating style and content on a nonlinear manifold. In: Proc. CVPR, vol. 1, pp. 478–485 (2004)
Fablet, R., Black, M.J.: Automatic detection and tracking of human motion with a view-based representation. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 476–491. Springer, Heidelberg (2002)
Gross, R., Shi, J.: The cmu motion of body (mobo) database. Technical Report TR-01-18, Carnegie Mellon University (2001)
Howe, N.R., Leventon, M.E., Freeman, W.T.: Bayesian reconstruction of 3d human motion from single-camera video. In: Proc. NIPS (1999)
De Lathauwer, L., de Moor, B., Vandewalle, J.: A multilinear singular value decomposiiton. SIAM Journal On Matrix Analysis and Applications 21 (4), 1253–1278 (2000)
De Lathauwer, L., de Moor, B., Vandewalle, J.: On the best rank-1 and rank-(r1, r2,..., rn) approximation of higher-order tensors. SIAM Journal On Matrix Analysis and Applications 21(4), 1324–1342 (2000)
Mori, G., Malik, J.: Estimating human body configurations using shape context matching. In: Proc. ECCV, pp. 666–680 (2002)
Turk, M., Pentland, A.: Eigenfaces for recognition. Journal of Cognitive Neuroscience 3(1), 71–86 (1991)
Murase, H., Nayar, S.: Visual learning and recognition of 3d objects from appearance. IJCV 14, 5–24 (1995)
Poggio, T., Girosi, F.: Networks for approximation and learning. Proceedings of the IEEE 78(9), 1481–1497 (1990)
Rosales, R., Athitsos, V., Sclaroff, S.: 3d hand pose reconstruction using specialized mappings. In: Proc. ICCV, pp. 378–387 (2001)
Rosales, R., Sclaroff, S.: Specialized mappings and the estimation of human body pose from a single image. In: Workshop on Human Motion, pp. 19–24 (2000)
Roweis, S., Saul, L.: Nonlinear dimensionality reduction by locally linear embedding. Sciene 290(5500), 2323–2326 (2000)
Schölkopf, B., Smola, A.: Learning with Kernels: Support Vector Machines, Regularization, Optimization and Beyond. The MIT Press, Cambridge (2002)
Shakhnarovich, G., Viola, P., Darrell, T.: Fast pose estimation with parameter-sensitive hashing. In: Proc. ICCV, pp. 750–759 (2003)
Sminchisescu, C., Jepson, A.: Generative modeling of continuous non-linearly embedded visual inference. In: Proc. ICML, pp. 140–147 (2004)
Tenenbaum, J.: Mapping a manifold of perceptual observations. In: Proc. NIPS, vol. 10, pp. 682–688 (1998)
Tenenbaum, J.B., Freeman, W.T.: Separating style and content with biliear models. Neural Computation 12, 1247–1283 (2000)
Toyama, K., Blake, A.: Probabilistic tracking in a metric space. In: Proc. ICCV, pp. 50–59 (2001)
Vasilescu, M.A.O.: Human motion signatures: Analysis, synthesis,recogntion. In: Proc. ICPR, vol. 3, pp. 456–460 (2002)
Vasilescu, M.A.O., Terzopoulos, D.: Multilinear subspace analysis of image ensembles. In: Proc. CVPR, pp. 93–99 (2003)
Wang, Q., Xu, G., Ai, H.: Learning object intrinsic structure for robust visual tracking. In: Proc. CVPR, vol. 2, pp. 227–233 (2003)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Lee, CS., Elgammal, A. (2007). Homeomorphic Manifold Analysis: Learning Decomposable Generative Models for Human Motion Analysis. In: Vidal, R., Heyden, A., Ma, Y. (eds) Dynamical Vision. WDV WDV 2006 2005. Lecture Notes in Computer Science, vol 4358. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-70932-9_8
Download citation
DOI: https://doi.org/10.1007/978-3-540-70932-9_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-70931-2
Online ISBN: 978-3-540-70932-9
eBook Packages: Computer ScienceComputer Science (R0)