Transformer dual feature enhancement based pedestrian re-identification algorithm

Chunyu Zhang; Jin Li

doi:10.1117/12.2671182

29 March 2023 Transformer dual feature enhancement based pedestrian re-identification algorithm

Chunyu Zhang, Jin Li

Proceedings Volume 12594, Second International Conference on Electronic Information Engineering and Computer Communication (EIECC 2022); 1259424 (2023) https://doi.org/10.1117/12.2671182
Event: Second International Conference on Electronic Information Engineering and Computer Communication (EIECC 2022), 2022, Xi'an, China

Abstract

Pedestrian re-identification is an integral part of surveillance video analysis, and the field of pedestrian re-identification has been growing rapidly in recent years with the development of deep learning. Most existing pedestrian re-identification methods are based on convolutional neural network deep learning models, and most studies consider learning representations from individual images, ignoring the potential interactions between them. In this paper, we propose a dual feature-enhanced pedestrian re-identification method based on Transformer architecture, which learns high discriminative features of pedestrians, suppresses the influence of irrelevant features on the network, and explicitly models the interactions between all input images to more fully learn the pedestrian feature representations from different perspectives, thus making the network more accurate and robust in overall recognition. Experiments with the model on four publicly available pedestrian re-identification datasets demonstrate that all evaluation metrics are higher than most of the current mainstream pedestrian re-identification models.

Citation Download Citation

Chunyu Zhang and Jin Li "Transformer dual feature enhancement based pedestrian re-identification algorithm", Proc. SPIE 12594, Second International Conference on Electronic Information Engineering and Computer Communication (EIECC 2022), 1259424 (29 March 2023); https://doi.org/10.1117/12.2671182

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
9 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Transformers

Education and training

Matrices

Feature extraction

Detection and tracking algorithms

Data modeling

Convolution

Keywords/Phrases

Search In:

Publication Years