Optimization of Person Re-Identification through Visual Descriptors

Naima Mubariz, Saba Mumtaz, M. M. Hamayun, M. M. Fraz

2018

Abstract

Person re-identification is a complex computer vision task which provides authorities a valuable tool for maintaining high level security. In surveillance applications, human appearance is considered critical since it possesses high discriminating power. Many re-identification algorithms have been introduced that employ a combination of visual features which solve one particular challenge of re-identification. This paper presents a new type of feature descriptor which incorporates multiple recently introduced visual feature representations such as Gaussian of Gaussian (GOG) andWeighted Histograms of Overlapping Stripes (WHOS) latest version into a single descriptor. Both these feature types demonstrate complementary properties that creates greater overall robustness to re-identification challenges such as variations in lighting, pose, background etc. The new descriptor is evaluated on several benchmark datasets such as VIPeR, CAVIAR4REID, GRID, 3DPeS, iLIDS, ETHZ1 and PRID450s and compared with several state-of-the-art methods to demonstrate effectiveness of the proposed approach.

Paper Citation

in Harvard Style

Mubariz N., Mumtaz S., Hamayun M. and Fraz M. (2018). Optimization of Person Re-Identification through Visual Descriptors. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 4: VISAPP; ISBN 978-989-758-290-5, SciTePress, pages 348-355. DOI: 10.5220/0006613303480355

in Bibtex Style

@conference{visapp18,
author={Naima Mubariz and Saba Mumtaz and M. M. Hamayun and M. M. Fraz},
title={Optimization of Person Re-Identification through Visual Descriptors},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 4: VISAPP},
year={2018},
pages={348-355},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006613303480355},
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 4: VISAPP
TI - Optimization of Person Re-Identification through Visual Descriptors
SN - 978-989-758-290-5
AU - Mubariz N.
AU - Mumtaz S.
AU - Hamayun M.
AU - Fraz M.
PY - 2018
SP - 348
EP - 355
DO - 10.5220/0006613303480355
PB - SciTePress