Two View Geometry Estimation by Determinant Minimization

Lorenzo Sorgi, Andrey Bushnevskiy

2016

Abstract

Two view geometry estimation, the task of inferring the relative pose between two cameras using only the image content, is one of the fundamental and most studied problems in Computer Vision. In this paper we present a new approach for two view geometry estimation, based on the minimization of an objective function given by the overall volume of the tetrahedrons identified in 3D space by pairs of corresponding feature points. This error measure is equivalent to the determinant of a real valued square matrix, function of the point match coordinates in the camera space, and we show how to minimize it taking advantage of the Perturbation Theorem. Test performed on synthetic and real dataset confirm an increased estimation accuracy compared to the state-of-art.

Paper Citation

in Harvard Style

Sorgi L. and Bushnevskiy A. (2016). Two View Geometry Estimation by Determinant Minimization.In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016) ISBN 978-989-758-175-5, pages 590-594. DOI: 10.5220/0005677405900594

in Bibtex Style

@conference{visapp16,
author={Lorenzo Sorgi and Andrey Bushnevskiy},
title={Two View Geometry Estimation by Determinant Minimization},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016)},
year={2016},
pages={590-594},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005677405900594},
isbn={978-989-758-175-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016)
TI - Two View Geometry Estimation by Determinant Minimization
SN - 978-989-758-175-5
AU - Sorgi L.
AU - Bushnevskiy A.
PY - 2016
SP - 590
EP - 594
DO - 10.5220/0005677405900594