Abstract
Traditional vehicle re-identification (ReID) approaches, based on visible spectrum data achieve high performance, but have limited capability of real-life applications, as they perform poorly under occluded visibility conditions, such as night-time and bad weather. In such cases, the use of infrared spectrum thermal imagery offers complementary and persistent information when the visual data contribution is inadequate. It is therefore highly beneficial to create a vehicle ReID framework that can exploit both modalities, if available, and is able to apply cross-modality matching, when ReID is required across single modal sensors. This is an extremely challenging task because the nature of the two data modalities induces high discrepancy between the two domains. In this paper we propose a robust end-to-end 2-stream vehicle ReID system that aims to solve the multi-modal and cross-modal ReID problem together by minimising the domain shift between infrared and visible distributions. Our framework consists of a shared network part, following the 2 independent streams, to extract shareable features, along with a domain alignment technique to narrow the gap between the two domains and inter-modality learning to address the cross-domain matching problem. The proposed system achieves state-of-the-art results on RGBN300 dataset, when both modalities are available at inference time. Moreover, our work is the first to explore the cross-modal settings for vehicle ReID and attempts to reduce the performance drop of the cross-modal scenario, when the query and the gallery images come from different modalities. We first measure the baseline cross-modal performance, and then prove that the proposed method improves up to 11% in mAP and 16% in Rank-1 score against the baseline.
Original language | English |
---|---|
Title of host publication | Proceedings of the 26th International Conference on Pattern Recognition |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 2728-2734 |
Number of pages | 7 |
ISBN (Electronic) | 9781665490627 |
DOIs | |
Publication status | Published - 29 Nov 2022 |
Event | International Conference on Pattern Recognition - Montreal, Canada Duration: 21 Aug 2022 → 25 Aug 2022 Conference number: 26th https://www.icpr2022.com/ http://www.free-ebooks.net/ |
Publication series
Name | International Conference on Pattern Recognition (ICPR) |
---|---|
Publisher | IEEE |
ISSN (Electronic) | 2831-7475 |
Conference
Conference | International Conference on Pattern Recognition |
---|---|
Abbreviated title | ICPR |
Country/Territory | Canada |
City | Montreal |
Period | 21/08/2022 → 25/08/2022 |
Internet address |
Fingerprint
Dive into the research topics of 'Closing the domain gap for cross-modal visible-infrared vehicle re-identification'. Together they form a unique fingerprint.Student theses
-
Vehicle re-identification from multi-modal vision sensors with deep metric learning
Kamenou, E. (Author), Martinez del Rincon, J. (Supervisor) & Miller, P. (Supervisor), Jul 2024Student thesis: Doctoral Thesis › Doctor of Philosophy
File