Edge based Foreground Background Estimation with Interior/Exterior Classification

Gianni Allebosch, David Van Hamme, Francis Deboeverie, Peter Veelaert, Wilfried Philips

2015

Abstract

Foreground background estimation is an essential task in many video analysis applications. Considerable improvements are still possible, especially concerning light condition invariance. In this paper, we propose a novel algorithm which attends to this requirement. We use modified Local Ternary Pattern (LTP) descriptors to find likely strong and stable “foreground gradient” locations. The proposed algorithm then classifies pixels as interior or exterior, using a shortest path algorithm, which proves to be robust against contour gaps.

Download


Paper Citation


in Harvard Style

Allebosch G., Van Hamme D., Deboeverie F., Veelaert P. and Philips W. (2015). Edge based Foreground Background Estimation with Interior/Exterior Classification . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-091-8, pages 369-376. DOI: 10.5220/0005358003690376

in Bibtex Style

@conference{visapp15,
author={Gianni Allebosch and David Van Hamme and Francis Deboeverie and Peter Veelaert and Wilfried Philips},
title={Edge based Foreground Background Estimation with Interior/Exterior Classification},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={369-376},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005358003690376},
isbn={978-989-758-091-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015)
TI - Edge based Foreground Background Estimation with Interior/Exterior Classification
SN - 978-989-758-091-8
AU - Allebosch G.
AU - Van Hamme D.
AU - Deboeverie F.
AU - Veelaert P.
AU - Philips W.
PY - 2015
SP - 369
EP - 376
DO - 10.5220/0005358003690376