Articulated motion estimation from a monocular image sequence using spherical tangent bundles
Lists
Only you see this
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.
BibTeX
@inproceedings{leonardos2016articulated,
author = {Spyridon Leonardos and Xiaowei Zhou and Kostas Daniilidis},
title = {{Articulated motion estimation from a monocular image sequence using spherical tangent bundles}},
booktitle = {IEEE International Conference on Robotics and Automation},
year = {2016},
doi = {10.1109/icra.2016.7487183},
}Loading related content...