Analysis of Recent Re-Identification Architectures for Tracking-by-Detection Paradigm in Multi-Object Tracking

Haruya Ishikawa, Masaki Hayashi, Trong Huy Phan, Kazuma Yamamoto, Makoto Masuda, Yoshimitsu Aoki

2021

Abstract

Person re-identification is a vital module of the tracking-by-detection framework for online multi-object tracking. Despite recent advances in multi-object tracking and person re-identification, inadequate attention was given to integrating these technologies to provide a robust multi-object tracker. In this work, we combine modern state-of-the-art re-identification models and modeling techniques on the basic tracking-by-detection framework and benchmark them on heavily occluded scenes to understand their effect. We hypothesize that temporal modeling for re-identification is crucial for training robust re-identification models for they are conditioned on sequences containing occlusions. Along with traditional image-based re-identification methods, we analyze temporal modeling methods used in video-based re-identification tasks. We also train re-identification models with different embedding methods, including triplet loss, and analyze their effect. We benchmark the re-identification models on the challenging MOT20 dataset containing crowded scenes with various occlusions. We provide a thorough assessment and investigation of the usage of modern re-identification modeling methods and prove that these methods are, in fact, effective for multi-object tracking. Compared to baseline methods, results show that these models can provide robust re-identification proved by improvements in the number of identity switching, MOTA, IDF1, and other metrics.

Paper Citation

in Harvard Style

Ishikawa H., Hayashi M., Phan T., Yamamoto K., Masuda M. and Aoki Y. (2021). Analysis of Recent Re-Identification Architectures for Tracking-by-Detection Paradigm in Multi-Object Tracking. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 234-244. DOI: 10.5220/0010341502340244

in Bibtex Style

@conference{visapp21,
author={Haruya Ishikawa and Masaki Hayashi and Trong Huy Phan and Kazuma Yamamoto and Makoto Masuda and Yoshimitsu Aoki},
title={Analysis of Recent Re-Identification Architectures for Tracking-by-Detection Paradigm in Multi-Object Tracking},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP},
year={2021},
pages={234-244},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010341502340244},
isbn={978-989-758-488-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP
TI - Analysis of Recent Re-Identification Architectures for Tracking-by-Detection Paradigm in Multi-Object Tracking
SN - 978-989-758-488-6
AU - Ishikawa H.
AU - Hayashi M.
AU - Phan T.
AU - Yamamoto K.
AU - Masuda M.
AU - Aoki Y.
PY - 2021
SP - 234
EP - 244
DO - 10.5220/0010341502340244
PB - SciTePress