Articulated motion estimation from a monocular image sequence using spherical tangent bundles

Spyridon Leonardos, Xiaowei Zhou, Kostas Daniilidis

Abstract: We propose a second order stochastic dynamical model for generic articulated objects whose state space is a Riemannian manifold naturally suggested by the articulation constraints. We derive the equations of a Riemannian Extended Kalman Filter to perform the structure estimation from an image sequence captured by a perspective camera. In order to theoretically validate our approach, we prove that the proposed model is locally weakly observable. Finally, we report quantitative results on both synthetic data and on real sequences from the CMU Mocap dataset.