Robust Vehicle Re-identification via Rigid Structure Prior

Authors: Minyue Jiang, Xuanmeng Zhang, Yue Yu, Zechen Bai, Zhedong Zheng, Zhigang Wang, Jian Wang, Xiao Tan, Hao Sun, Errui Ding, Yi Yang

Published in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshop of AI City Challenge on City-Scale Multi-Camera Vehicle Re-Identification (the 2nd Place of Track 2), 2021

Recommended citation: Minyue Jiang, Xuanmeng Zhang, Yue Yu, Zechen Bai, Zhedong Zheng, Zhigang Wang, Jian Wang, Xiao Tan, Hao Sun, Errui Ding, Yi Yang, "Robust Vehicle Re-identification via Rigid Structure Prior." CVPR Workshop of AI City Challenge on City-Scale Multi-Camera Vehicle Re-Identification (the 2nd Place of Track 2), 2021.
Download PDF: https://zdzheng.xyz/files/2021/CVPRW-2021-VehicleReid.pdf

Code is available at: https://github.com/Xuanmeng-Zhang/AICITY2021-Track2

Abstract: Vehicle re-identification (re-id) is one of the most important components in the current intelligence transport system, benefiting both the smart traffic management and the optimal path planning. In this paper, we focus on developing a robust part-aware structure-based vehicle re-id system against the massive appearance changes due to the pose and illumination variants. Specifically, we apply the strong convolutional neural networks to extract the visual representation, which is based on the detected vehicle images. Taking one step further, we deploy a part detector to recognize different vehicle parts, such as front, back, left, and right, which explicitly introduce the prior knowledge on the structure of the rigid objective, i.e., vehicle. With the geometry information, we further harness different part feature extractors to filter wrong matches. By using this simple but effective strategy, we remove the hard negative candidates while maintaining high recall accuracy, combing general global-level coarse-grained re-id feature models with part-level fine-grained features. We achieved 71.51\% mAP in the vehicle re-id track of the AI City Challenge 2021, which verified the effectiveness and scalability of the proposed structure-based method.

@inproceedings{zheng2021robust,
author = "Jiang, Minyue and Zhang, Xuanmeng and Yu, Yue and Bai, Zechen and Zheng, Zhedong and Wang, Zhigang and Wang, Jian and Tan, Xiao and Sun, Hao and Ding, Errui and Yang, Yi",
title = "Robust Vehicle Re-identification via Rigid Structure Prior",
abstract = "Vehicle re-identification (re-id) is one of the most important components in the current intelligence transport system, benefiting both the smart traffic management and the optimal path planning. In this paper, we focus on developing a robust part-aware structure-based vehicle re-id system against the massive appearance changes due to the pose and illumination variants. Specifically, we apply the strong convolutional neural networks to extract the visual representation, which is based on the detected vehicle images. Taking one step further, we deploy a part detector to recognize different vehicle parts, such as front, back, left, and right, which explicitly introduce the prior knowledge on the structure of the rigid objective, i.e., vehicle. With the geometry information, we further harness different part feature extractors to filter wrong matches. By using this simple but effective strategy, we remove the hard negative candidates while maintaining high recall accuracy, combing general global-level coarse-grained re-id feature models with part-level fine-grained features. We achieved 71.51\\% mAP in the vehicle re-id track of the AI City Challenge 2021, which verified the effectiveness and scalability of the proposed structure-based method.",
booktitle = "CVPR Workshop of AI City Challenge on City-Scale Multi-Camera Vehicle Re-Identification (the 2nd Place of Track 2)",
code = "https://github.com/Xuanmeng-Zhang/AICITY2021-Track2",
url = "https://zdzheng.xyz/files/2021/CVPRW-2021-VehicleReid.pdf",
year = "2021" }