A Novel Geo-Localization Method for UAV and Satellite Images Using Cross-View Consistent Attention
Geo-localization has been widely applied as an important technique to get the longitude and latitude for unmanned aerial vehicle (UAV) navigation in outdoor flight. Due to the possible interference and blocking of GPS signals, the method based on image retrieval, which is less likely to be interfere...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-09-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/15/19/4667 |
_version_ | 1797575227754938368 |
---|---|
author | Zhuofan Cui Pengwei Zhou Xiaolong Wang Zilun Zhang Yingxuan Li Hongbo Li Yu Zhang |
author_facet | Zhuofan Cui Pengwei Zhou Xiaolong Wang Zilun Zhang Yingxuan Li Hongbo Li Yu Zhang |
author_sort | Zhuofan Cui |
collection | DOAJ |
description | Geo-localization has been widely applied as an important technique to get the longitude and latitude for unmanned aerial vehicle (UAV) navigation in outdoor flight. Due to the possible interference and blocking of GPS signals, the method based on image retrieval, which is less likely to be interfered with, has received extensive attention in recent years. The geo-localization of UAVs and satellites can be achieved by querying pre-obtained satellite images with GPS-tagged and drone images from different perspectives. In this paper, an image transformation technique is used to extract cross-view geo-localization information from UAVs and satellites. A single-stage training method in UAV and satellite geo-localization is first proposed, which simultaneously realizes cross-view feature extraction and image retrieval, and achieves higher accuracy than existing multi-stage training techniques. A novel piecewise soft-margin triplet loss function is designed to avoid model parameters being trapped in suboptimal sets caused by the lack of constraint on positive and negative samples. The results illustrate that the proposed loss function enhances image retrieval accuracy and realizes a better convergence. Moreover, a data augmentation method for satellite images is proposed to overcome the disproportionate numbers of image samples. On the benchmark University-1652, the proposed method achieves the state-of-the-art result with a 6.67% improvement in recall rate (R@1) and 6.13% in average precision (AP). All codes will be publicized to promote reproducibility. |
first_indexed | 2024-03-10T21:36:46Z |
format | Article |
id | doaj.art-5b5873fcc3d8482e86d5a3e43084131e |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-10T21:36:46Z |
publishDate | 2023-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-5b5873fcc3d8482e86d5a3e43084131e2023-11-19T14:58:16ZengMDPI AGRemote Sensing2072-42922023-09-011519466710.3390/rs15194667A Novel Geo-Localization Method for UAV and Satellite Images Using Cross-View Consistent AttentionZhuofan Cui0Pengwei Zhou1Xiaolong Wang2Zilun Zhang3Yingxuan Li4Hongbo Li5Yu Zhang6State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou 310012, ChinaState Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou 310012, ChinaState Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou 310012, ChinaCollege of Computer Science, Zhejiang University, Hangzhou 310012, ChinaState Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou 310012, ChinaBeijing Geekplus Technology Co., Ltd., 7/F, Block D, Beijing Cultural and Creative Building, 30 Beiyuan Road, Chaoyang District, Beijing 100107, ChinaState Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou 310012, ChinaGeo-localization has been widely applied as an important technique to get the longitude and latitude for unmanned aerial vehicle (UAV) navigation in outdoor flight. Due to the possible interference and blocking of GPS signals, the method based on image retrieval, which is less likely to be interfered with, has received extensive attention in recent years. The geo-localization of UAVs and satellites can be achieved by querying pre-obtained satellite images with GPS-tagged and drone images from different perspectives. In this paper, an image transformation technique is used to extract cross-view geo-localization information from UAVs and satellites. A single-stage training method in UAV and satellite geo-localization is first proposed, which simultaneously realizes cross-view feature extraction and image retrieval, and achieves higher accuracy than existing multi-stage training techniques. A novel piecewise soft-margin triplet loss function is designed to avoid model parameters being trapped in suboptimal sets caused by the lack of constraint on positive and negative samples. The results illustrate that the proposed loss function enhances image retrieval accuracy and realizes a better convergence. Moreover, a data augmentation method for satellite images is proposed to overcome the disproportionate numbers of image samples. On the benchmark University-1652, the proposed method achieves the state-of-the-art result with a 6.67% improvement in recall rate (R@1) and 6.13% in average precision (AP). All codes will be publicized to promote reproducibility.https://www.mdpi.com/2072-4292/15/19/4667geo-localizationUAVsatellitetransformercross-view |
spellingShingle | Zhuofan Cui Pengwei Zhou Xiaolong Wang Zilun Zhang Yingxuan Li Hongbo Li Yu Zhang A Novel Geo-Localization Method for UAV and Satellite Images Using Cross-View Consistent Attention Remote Sensing geo-localization UAV satellite transformer cross-view |
title | A Novel Geo-Localization Method for UAV and Satellite Images Using Cross-View Consistent Attention |
title_full | A Novel Geo-Localization Method for UAV and Satellite Images Using Cross-View Consistent Attention |
title_fullStr | A Novel Geo-Localization Method for UAV and Satellite Images Using Cross-View Consistent Attention |
title_full_unstemmed | A Novel Geo-Localization Method for UAV and Satellite Images Using Cross-View Consistent Attention |
title_short | A Novel Geo-Localization Method for UAV and Satellite Images Using Cross-View Consistent Attention |
title_sort | novel geo localization method for uav and satellite images using cross view consistent attention |
topic | geo-localization UAV satellite transformer cross-view |
url | https://www.mdpi.com/2072-4292/15/19/4667 |
work_keys_str_mv | AT zhuofancui anovelgeolocalizationmethodforuavandsatelliteimagesusingcrossviewconsistentattention AT pengweizhou anovelgeolocalizationmethodforuavandsatelliteimagesusingcrossviewconsistentattention AT xiaolongwang anovelgeolocalizationmethodforuavandsatelliteimagesusingcrossviewconsistentattention AT zilunzhang anovelgeolocalizationmethodforuavandsatelliteimagesusingcrossviewconsistentattention AT yingxuanli anovelgeolocalizationmethodforuavandsatelliteimagesusingcrossviewconsistentattention AT hongboli anovelgeolocalizationmethodforuavandsatelliteimagesusingcrossviewconsistentattention AT yuzhang anovelgeolocalizationmethodforuavandsatelliteimagesusingcrossviewconsistentattention AT zhuofancui novelgeolocalizationmethodforuavandsatelliteimagesusingcrossviewconsistentattention AT pengweizhou novelgeolocalizationmethodforuavandsatelliteimagesusingcrossviewconsistentattention AT xiaolongwang novelgeolocalizationmethodforuavandsatelliteimagesusingcrossviewconsistentattention AT zilunzhang novelgeolocalizationmethodforuavandsatelliteimagesusingcrossviewconsistentattention AT yingxuanli novelgeolocalizationmethodforuavandsatelliteimagesusingcrossviewconsistentattention AT hongboli novelgeolocalizationmethodforuavandsatelliteimagesusingcrossviewconsistentattention AT yuzhang novelgeolocalizationmethodforuavandsatelliteimagesusingcrossviewconsistentattention |