VOC-ReID: Vehicle Re-identification based on Vehicle-Orientation-Camera

TL;DR

This paper introduces VOC-ReID, a vehicle re-identification method that reduces background and shape bias by incorporating vehicle orientation and camera information, achieving high accuracy in challenging scenarios.

Contribution

The paper presents a novel approach combining vehicle, orientation, and camera re-identification to improve vehicle re-ID accuracy and introduces a strong baseline with data augmentation techniques.

Findings

Achieved second place in NVIDIA AI City Challenge 2020.

Effective reduction of background and shape bias in vehicle re-identification.

Enhanced baseline performance with tricks and weakly supervised data augmentation.

Abstract

Vehicle re-identification is a challenging task due to high intra-class variances and small inter-class variances. In this work, we focus on the failure cases caused by similar background and shape. They pose serve bias on similarity, making it easier to neglect fine-grained information. To reduce the bias, we propose an approach named VOC-ReID, taking the triplet vehicle-orientation-camera as a whole and reforming background/shape similarity as camera/orientation re-identification. At first, we train models for vehicle, orientation and camera re-identification respectively. Then we use orientation and camera similarity as penalty to get final similarity. Besides, we propose a high performance baseline boosted by bag of tricks and weakly supervised data augmentation. Our algorithm achieves the second place in vehicle re-identification at the NVIDIA AI City Challenge 2020.