Aerial-Ground Cross-View Vehicle Re-Identification: A Benchmark Dataset and Baseline

Vehicle re-identification (Re-ID) is a critical computer vision task that aims to match the same vehicle across spatially distributed cameras, especially in the context of remote sensing imagery. While prior research has primarily focused on Re-ID using remote sensing images captured from similar, t...

Full description

Saved in:
Bibliographic Details
Main Authors: Linzhi Shang, Chen Min, Juan Wang, Liang Xiao, Dawei Zhao, Yiming Nie
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/15/2653
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849406457876840448
author Linzhi Shang
Chen Min
Juan Wang
Liang Xiao
Dawei Zhao
Yiming Nie
author_facet Linzhi Shang
Chen Min
Juan Wang
Liang Xiao
Dawei Zhao
Yiming Nie
author_sort Linzhi Shang
collection DOAJ
description Vehicle re-identification (Re-ID) is a critical computer vision task that aims to match the same vehicle across spatially distributed cameras, especially in the context of remote sensing imagery. While prior research has primarily focused on Re-ID using remote sensing images captured from similar, typically elevated viewpoints, these settings do not fully reflect complex aerial-ground collaborative remote sensing scenarios. In this work, we introduce a novel and challenging task: aerial-ground cross-view vehicle Re-ID, which involves retrieving vehicles in ground-view image galleries using query images captured from aerial (top-down) perspectives. This task is increasingly relevant due to the integration of drone-based surveillance and ground-level monitoring in multi-source remote sensing systems, yet it poses substantial challenges due to significant appearance variations between aerial and ground views. To support this task, we present AGID (Aerial-Ground Vehicle Re-Identification), the first benchmark dataset specifically designed for aerial-ground cross-view vehicle Re-ID. AGID comprises 20,785 remote sensing images of 834 vehicle identities, collected using drones and fixed ground cameras. We further propose a novel method, Enhanced Self-Correlation Feature Computation (ESFC), which enhances spatial relationships between semantically similar regions and incorporates shape information to improve feature discrimination. Extensive experiments on the AGID dataset and three widely used vehicle Re-ID benchmarks validate the effectiveness of our method, which achieves a Rank-1 accuracy of 69.0% on AGID, surpassing state-of-the-art approaches by 2.1%.
format Article
id doaj-art-e65aec9ab055401ebe3328e3b5f14b21
institution Kabale University
issn 2072-4292
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-e65aec9ab055401ebe3328e3b5f14b212025-08-20T03:36:22ZengMDPI AGRemote Sensing2072-42922025-07-011715265310.3390/rs17152653Aerial-Ground Cross-View Vehicle Re-Identification: A Benchmark Dataset and BaselineLinzhi Shang0Chen Min1Juan Wang2Liang Xiao3Dawei Zhao4Yiming Nie5Defense Innovation Institute, Beijing 100071, ChinaInstitute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, ChinaDepartment of Computer Science and Technology, Tsinghua University, Beijing 100084, ChinaDefense Innovation Institute, Beijing 100071, ChinaDefense Innovation Institute, Beijing 100071, ChinaDefense Innovation Institute, Beijing 100071, ChinaVehicle re-identification (Re-ID) is a critical computer vision task that aims to match the same vehicle across spatially distributed cameras, especially in the context of remote sensing imagery. While prior research has primarily focused on Re-ID using remote sensing images captured from similar, typically elevated viewpoints, these settings do not fully reflect complex aerial-ground collaborative remote sensing scenarios. In this work, we introduce a novel and challenging task: aerial-ground cross-view vehicle Re-ID, which involves retrieving vehicles in ground-view image galleries using query images captured from aerial (top-down) perspectives. This task is increasingly relevant due to the integration of drone-based surveillance and ground-level monitoring in multi-source remote sensing systems, yet it poses substantial challenges due to significant appearance variations between aerial and ground views. To support this task, we present AGID (Aerial-Ground Vehicle Re-Identification), the first benchmark dataset specifically designed for aerial-ground cross-view vehicle Re-ID. AGID comprises 20,785 remote sensing images of 834 vehicle identities, collected using drones and fixed ground cameras. We further propose a novel method, Enhanced Self-Correlation Feature Computation (ESFC), which enhances spatial relationships between semantically similar regions and incorporates shape information to improve feature discrimination. Extensive experiments on the AGID dataset and three widely used vehicle Re-ID benchmarks validate the effectiveness of our method, which achieves a Rank-1 accuracy of 69.0% on AGID, surpassing state-of-the-art approaches by 2.1%.https://www.mdpi.com/2072-4292/17/15/2653aerial-groundcross-viewremote sensingvehicle re-identification
spellingShingle Linzhi Shang
Chen Min
Juan Wang
Liang Xiao
Dawei Zhao
Yiming Nie
Aerial-Ground Cross-View Vehicle Re-Identification: A Benchmark Dataset and Baseline
Remote Sensing
aerial-ground
cross-view
remote sensing
vehicle re-identification
title Aerial-Ground Cross-View Vehicle Re-Identification: A Benchmark Dataset and Baseline
title_full Aerial-Ground Cross-View Vehicle Re-Identification: A Benchmark Dataset and Baseline
title_fullStr Aerial-Ground Cross-View Vehicle Re-Identification: A Benchmark Dataset and Baseline
title_full_unstemmed Aerial-Ground Cross-View Vehicle Re-Identification: A Benchmark Dataset and Baseline
title_short Aerial-Ground Cross-View Vehicle Re-Identification: A Benchmark Dataset and Baseline
title_sort aerial ground cross view vehicle re identification a benchmark dataset and baseline
topic aerial-ground
cross-view
remote sensing
vehicle re-identification
url https://www.mdpi.com/2072-4292/17/15/2653
work_keys_str_mv AT linzhishang aerialgroundcrossviewvehiclereidentificationabenchmarkdatasetandbaseline
AT chenmin aerialgroundcrossviewvehiclereidentificationabenchmarkdatasetandbaseline
AT juanwang aerialgroundcrossviewvehiclereidentificationabenchmarkdatasetandbaseline
AT liangxiao aerialgroundcrossviewvehiclereidentificationabenchmarkdatasetandbaseline
AT daweizhao aerialgroundcrossviewvehiclereidentificationabenchmarkdatasetandbaseline
AT yimingnie aerialgroundcrossviewvehiclereidentificationabenchmarkdatasetandbaseline