A Triplet-learnt Coarse-to-Fine Reranking for Vehicle Re-identification

Efklidis Katsaros, Henri Bouma, Arthur van Rooijen, Elise Dusseldorp

Abstract

Vehicle re-identification refers to the task of matching the same query vehicle across non-overlapping cameras and diverse viewpoints. Research interest on the field emerged with intelligent transportation systems and the necessity for public security maintenance. Compared to person, vehicle re-identification is more intricate, facing the challenges of lower intra-class and higher inter-class similarities. Motivated by deep metric learning advances, we propose a novel, triplet-learnt coarse-to-fine reranking scheme (C2F-TriRe) to address vehicle re-identification. Coarse vehicle features conduct the baseline ranking. Thereafter, a fully connected network maps features to viewpoints. Simultaneously, windshields are detected and respective fine features are extracted to capture custom vehicle characteristics. Conditional to the viewpoint, coarse and fine features are combined to yield a robust reranking. The proposed scheme achieves state-of-the-art performance on the VehicleID dataset and outperforms our baselines by a large margin.

Download


Paper Citation


in Harvard Style

Katsaros E., Bouma H., van Rooijen A. and Dusseldorp E. (2020). A Triplet-learnt Coarse-to-Fine Reranking for Vehicle Re-identification.In Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-397-1, pages 518-525. DOI: 10.5220/0008974005180525


in Bibtex Style

@conference{icpram20,
author={Efklidis Katsaros and Henri Bouma and Arthur van Rooijen and Elise Dusseldorp},
title={A Triplet-learnt Coarse-to-Fine Reranking for Vehicle Re-identification},
booktitle={Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2020},
pages={518-525},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008974005180525},
isbn={978-989-758-397-1},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - A Triplet-learnt Coarse-to-Fine Reranking for Vehicle Re-identification
SN - 978-989-758-397-1
AU - Katsaros E.
AU - Bouma H.
AU - van Rooijen A.
AU - Dusseldorp E.
PY - 2020
SP - 518
EP - 525
DO - 10.5220/0008974005180525