Auto-labeling as a Minimization Problem with Virtual Occlusions
Abstract
In this paper we propose a fast algorithm for the automatic labeling of a set of predefined markers in an optical motion capture system. This algorithm is facing the problem as a minimization problem, using a virtual representation of the real model to predict possible occlusions that happen in the captured images. Moreover, we take advantage of the knowledge of the cameras parameters to solve potential labeling conflicts between markers.
BibTeX
@inproceedings {10.2312:LocalChapterEvents:CEIG:CEIG08:133-139,
booktitle = {CEIG 08 - Congreso Espanol de Informatica Grafica},
editor = {Luis Matey and Juan Carlos Torres},
title = {{Auto-labeling as a Minimization Problem with Virtual Occlusions}},
author = {Cuevas, A. and Rodriguez-Navarro, J. and Susin, A.},
year = {2008},
publisher = {The Eurographics Association},
ISBN = {978-3-905673-69-2},
DOI = {10.2312/LocalChapterEvents/CEIG/CEIG08/133-139}
}
booktitle = {CEIG 08 - Congreso Espanol de Informatica Grafica},
editor = {Luis Matey and Juan Carlos Torres},
title = {{Auto-labeling as a Minimization Problem with Virtual Occlusions}},
author = {Cuevas, A. and Rodriguez-Navarro, J. and Susin, A.},
year = {2008},
publisher = {The Eurographics Association},
ISBN = {978-3-905673-69-2},
DOI = {10.2312/LocalChapterEvents/CEIG/CEIG08/133-139}
}