Shared latent dynamical structure for three-dimensional human pose estimation

MingLei Tong, Hong Han, Wu Zhu

Abstract: In this paper, a shared latent dynamical model (SLDM) and its application in tracking 3D human motion from monocular videos are proposed by combining the ideas of Gaussian processes dynamical model with shared latent structure. When tracking in high-dimensional space, SLDM can map state space and observation space to a shared latent space of low dimensionality with associated dynamics. During off-line training, three mappings, including dynamical mapping in latent space and mappings from the latent space to both state space and observation space, are learned. This model can separate traditional human motion estimation in high-dimensional space into two steps: In the first step, the shared latent dynamical variables are estimated; in the second step, the human pose of high dimension is reconstructed. Experiments in human motion tracking from monocular videos using simulations and real images demonstrate that this human tracking method is efficient.

External IDs:dblp:journals/chinaf/TongHZ11