Feature Extraction using Downsampling for Person Re-identification with Low-resolution Images

Masashi Nishiyama, Takuya Endo, Yoshio Iwai

2022

Abstract

We investigate whether a downsampling process of high-resolution pedestrian images can improve person re-identification accuracy. Generally, deep-learning and machine-learning techniques are used to extract features that are unaffected by image resolution. However, it requires a large number of pairs of high- and low-resolution images acquired from the same person. Here, we consider a situation in which these resolution pairs cannot be collected. We extract features from low-resolution pedestrian images using only a simple downsampling process that requires no training resolution pairs. We collected image resolution datasets by changing the focal length of the camera lens and the distance from the person to the camera. We confirmed that the person re-identification accuracy of the downsampling process was superior to that of the upsampling. We also confirmed that the low-frequency components corresponding to the output of the downsampling process contain many discriminative features.

Paper Citation

in Harvard Style

Nishiyama M., Endo T. and Iwai Y. (2022). Feature Extraction using Downsampling for Person Re-identification with Low-resolution Images. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 351-358. DOI: 10.5220/0010815500003124

in Bibtex Style

@conference{visapp22,
author={Masashi Nishiyama and Takuya Endo and Yoshio Iwai},
title={Feature Extraction using Downsampling for Person Re-identification with Low-resolution Images},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP},
year={2022},
pages={351-358},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010815500003124},
isbn={978-989-758-555-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP
TI - Feature Extraction using Downsampling for Person Re-identification with Low-resolution Images
SN - 978-989-758-555-5
AU - Nishiyama M.
AU - Endo T.
AU - Iwai Y.
PY - 2022
SP - 351
EP - 358
DO - 10.5220/0010815500003124
PB - SciTePress