Combining Geometric- and View-Based Approaches for Articulated Pose Estimation
Abstract
In this paper we propose an efficient real-time approach that combines vision-based tracking and a view-based model to estimate the pose of a person. We introduce an appearance model that contains views of a person under various articulated poses. The appearance model is built and updated online. The main contribution consists of modeling, in each frame, the pose changes as a linear transformation of the view change. This linear model allows (i) for predicting the pose in a new image, and (ii) for obtaining a better estimate of the pose corresponding to a key frame. Articulated pose is computed by merging the estimation provided by the tracking-based algorithm and the linear prediction given by the view-based model.
Cite
Text
Demirdjian. "Combining Geometric- and View-Based Approaches for Articulated Pose Estimation." European Conference on Computer Vision, 2004. doi:10.1007/978-3-540-24672-5_15Markdown
[Demirdjian. "Combining Geometric- and View-Based Approaches for Articulated Pose Estimation." European Conference on Computer Vision, 2004.](https://mlanthology.org/eccv/2004/demirdjian2004eccv-combining/) doi:10.1007/978-3-540-24672-5_15BibTeX
@inproceedings{demirdjian2004eccv-combining,
title = {{Combining Geometric- and View-Based Approaches for Articulated Pose Estimation}},
author = {Demirdjian, David},
booktitle = {European Conference on Computer Vision},
year = {2004},
pages = {183-194},
doi = {10.1007/978-3-540-24672-5_15},
url = {https://mlanthology.org/eccv/2004/demirdjian2004eccv-combining/}
}