Nonlocal Regularizing Constraints in Variational Optical Flow

Joan Duran, Antoni Buades

2017

Abstract

Optical flow methods try to estimate a dense correspondence field describing the motion of the objects in an image sequence. We introduce novel nonlocal regularizing constraints for variational optical flow computation. While the use of similarity weights has been restricted to the regularization term so far, the proposed data terms permit to implicitly use the image geometry in order to regularize the flow and better locate motion discontinuities. The experimental results illustrate the superiority of the new constraints with respect to the classical brightness constancy assumption as well as to nonlocal regularization strategies.

Paper Citation

in Harvard Style

Duran J. and Buades A. (2017). Nonlocal Regularizing Constraints in Variational Optical Flow . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-227-1, pages 151-161. DOI: 10.5220/0006098501510161

in Bibtex Style

@conference{visapp17,
author={Joan Duran and Antoni Buades},
title={Nonlocal Regularizing Constraints in Variational Optical Flow},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={151-161},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006098501510161},
isbn={978-989-758-227-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017)
TI - Nonlocal Regularizing Constraints in Variational Optical Flow
SN - 978-989-758-227-1
AU - Duran J.
AU - Buades A.
PY - 2017
SP - 151
EP - 161
DO - 10.5220/0006098501510161