KERNEL SELECTION BY MUTUAL INFORMATION FOR NONPARAMETRIC OBJECT TRACKING

J. M. Berthommé, T. Chateau, M. Dhome

2012

Abstract

This paper presents a method to select kernels for the subsampling of nonparametric models used in realtime object tracking in video streams. We propose a method based on mutual information, inspired by the CMIM algorithm (Fleuret, 2004) for the selection of binary features. This builds, incrementally, a model of appearance of the object to follow, based on representative and independant kernels taken from points of that object. Experiments show gains, in terms of accuracy, compared to other sampling strategies.

Paper Citation

in Harvard Style

M. Berthommé J., Chateau T. and Dhome M. (2012). KERNEL SELECTION BY MUTUAL INFORMATION FOR NONPARAMETRIC OBJECT TRACKING . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-04-4, pages 373-376. DOI: 10.5220/0003833603730376

in Bibtex Style

@conference{visapp12,
author={J. M. Berthommé and T. Chateau and M. Dhome},
title={KERNEL SELECTION BY MUTUAL INFORMATION FOR NONPARAMETRIC OBJECT TRACKING},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={373-376},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003833603730376},
isbn={978-989-8565-04-4},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2012)
TI - KERNEL SELECTION BY MUTUAL INFORMATION FOR NONPARAMETRIC OBJECT TRACKING
SN - 978-989-8565-04-4
AU - M. Berthommé J.
AU - Chateau T.
AU - Dhome M.
PY - 2012
SP - 373
EP - 376
DO - 10.5220/0003833603730376