Countering Bias in Tracking Evaluations

Gustav Häger, Michael Felsberg, Fahad Khan

2018

Abstract

Recent years have witnessed a significant leap in visual object tracking performance mainly due to powerful features, sophisticated learning methods and the introduction of benchmark datasets. Despite this significant improvement, the evaluation of state-of-the-art object trackers still relies on the classical intersection over union (IoU) score. In this work, we argue that the object tracking evaluations based on classical IoU score are sub-optimal. As our first contribution, we theoretically prove that the IoU score is biased in the case of large target objects and favors over-estimated target prediction sizes. As our second contribution, we propose a new score that is unbiased with respect to target prediction size. We systematically evaluate our proposed approach on benchmark tracking data with variations in relative target size. Our empirical results clearly suggest that the proposed score is unbiased in general.

Download


Paper Citation


in Harvard Style

Häger G., Felsberg M. and Khan F. (2018). Countering Bias in Tracking Evaluations. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP; ISBN 978-989-758-290-5, SciTePress, pages 581-587. DOI: 10.5220/0006714805810587


in Bibtex Style

@conference{visapp18,
author={Gustav Häger and Michael Felsberg and Fahad Khan},
title={Countering Bias in Tracking Evaluations},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP},
year={2018},
pages={581-587},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006714805810587},
isbn={978-989-758-290-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP
TI - Countering Bias in Tracking Evaluations
SN - 978-989-758-290-5
AU - Häger G.
AU - Felsberg M.
AU - Khan F.
PY - 2018
SP - 581
EP - 587
DO - 10.5220/0006714805810587
PB - SciTePress