A triplet-learnt Coarse-to-Fine Reranking for Large Scale Vehicle Re-identification.

A triplet-learnt Coarse-to-Fine Reranking for Large Scale Vehicle Re-identification.

Katsaros, E.
Bouma, H.
van Rooijen, A.L.
van Dusseldorp, E.

2020

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.

Vehicle Re-identification
Deep Learning
Coarse-to-Fine
Computer Vision

http://resolver.tudelft.nl/uuid:41ff5633-32d1-440f-83af-d5a1b4027409

875267

TNO, Den Haag

Proceedings International Conference Pattern Recognition Applications and Methods ICPRAM, Valetta Malta 2020, 518-525

TNO Scriptie met dezelfde titel

conference paper