3D POSE ESTIMATION FROM SILHOUETTES IN CYCLIC ACTIVITIES ENCODED BY A DENSE GAUSSIANS MIXTURE MODEL
S. Amin Dadgar, Jean-Christophe Nebel, Dimitrios Makris
2010
Abstract
This paper presents a system for 3D Pose estimation of cyclic activities (e.g. walking, jogging). Principal Component Analysis is used to compress the high dimensional space of poses. Human activities are encoded by Hidden Markov Models, overlaid on Gaussian Mixture Models. A generative approach based on the Annealed Particle Filter is used to estimate poses from silhouettes derived by a monocular camera. Experimental results indicate the value of the proposed Dense Gaussian Mixture Model when initialised by a gait cycle.
DownloadPaper Citation
in Harvard Style
Amin Dadgar S., Nebel J. and Makris D. (2010). 3D POSE ESTIMATION FROM SILHOUETTES IN CYCLIC ACTIVITIES ENCODED BY A DENSE GAUSSIANS MIXTURE MODEL . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-028-3, pages 492-495. DOI: 10.5220/0002896004920495
in Bibtex Style
@conference{visapp10,
author={S. Amin Dadgar and Jean-Christophe Nebel and Dimitrios Makris},
title={3D POSE ESTIMATION FROM SILHOUETTES IN CYCLIC ACTIVITIES ENCODED BY A DENSE GAUSSIANS MIXTURE MODEL},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010)},
year={2010},
pages={492-495},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002896004920495},
isbn={978-989-674-028-3},
}
in EndNote Style
TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010)
TI - 3D POSE ESTIMATION FROM SILHOUETTES IN CYCLIC ACTIVITIES ENCODED BY A DENSE GAUSSIANS MIXTURE MODEL
SN - 978-989-674-028-3
AU - Amin Dadgar S.
AU - Nebel J.
AU - Makris D.
PY - 2010
SP - 492
EP - 495
DO - 10.5220/0002896004920495