Modeling Human Motion Using Manifold Learning and Factorized Generative Models

OF THE DISSERTATION Modeling Human Motion Using Manifold Learning and Factorized Generative Models by Chan-Su Lee Dissertation Director: Ahmed Elgammal Modeling the dynamic shape and appearance of articulated moving objects is essential for human motion analysis, tracking, synthesis, and other computer vision problems. Modeling the shape and appearance of human motion is challenging due to the high dimensionality of the articulated human motion, variations of shape and appearance from different views and in different people, and the nonlinearity in shape and appearance deformations in the observed sequences. Recent interest in modeling human motion is originated from the various potential real-world applications such as visual surveillance, human-computer interaction, video analysis, computer animation, etc. We present a novel framework to model dynamic shape and appearance using nonlinear manifold embedding and factorization. We investigate different representations to embed highdimensional human motion sequences in low dimensional spaces by supervised and unsupervised manifold learning techniques to achieve representations that capture the intrinsic structure of the motion. Nonlinear dimensionality reduction techniques based on visual data and kinematic data are applied to discover low dimensional intrinsic manifold representation for body configuration. Also, we investigate the use of supervised manifold learning from a known manifold topology to model deformation of manifolds from an ideal case. By learning nonlinear mapping from the embedding space to the input shape or appearance, we can generate shape