Visual Geolocalization for Aerial Vehicles via Fusion of Satellite Remote Sensing Imagery and Its Relative Depth Information
Visual geolocalization for aerial vehicles based on an analysis of Earth observation imagery is an effective method in GNSS-denied environments. However, existing methods for geographic location estimation have limitations: one relies on high-precision geodetic elevation data, which is costly, and t...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/13/2291 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849319934563188736 |
|---|---|
| author | Maoan Zhou Dongfang Yang Jieyu Liu Weibo Xu Xiong Qiu Yongfei Li |
| author_facet | Maoan Zhou Dongfang Yang Jieyu Liu Weibo Xu Xiong Qiu Yongfei Li |
| author_sort | Maoan Zhou |
| collection | DOAJ |
| description | Visual geolocalization for aerial vehicles based on an analysis of Earth observation imagery is an effective method in GNSS-denied environments. However, existing methods for geographic location estimation have limitations: one relies on high-precision geodetic elevation data, which is costly, and the other assumes a flat ground surface, ignoring elevation differences. This paper presents a novel aerial vehicle geolocalization method. It integrates 2D information and relative depth information, which are both from Earth observation images. Firstly, the aerial and reference remote sensing satellite images are fed into a feature-matching network to extract pixel-level feature-matching pairs. Then, a depth estimation network is used to estimate the relative depth of the satellite remote sensing image, thereby obtaining the relative depth information of the ground area within the field of view of the aerial image. Finally, high-confidence matching pairs with similar depth and uniform distribution are selected to estimate the geographic location of the aerial vehicle. Experimental results demonstrate that the proposed method outperforms existing ones in terms of geolocalization accuracy and stability. It eliminates reliance on elevation data or planar assumptions, thus providing a more adaptable and robust solution for aerial vehicle geolocalization in GNSS-denied environments. |
| format | Article |
| id | doaj-art-8cdd2967948a4d8eacbbfd88c543bc63 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-8cdd2967948a4d8eacbbfd88c543bc632025-08-20T03:50:16ZengMDPI AGRemote Sensing2072-42922025-07-011713229110.3390/rs17132291Visual Geolocalization for Aerial Vehicles via Fusion of Satellite Remote Sensing Imagery and Its Relative Depth InformationMaoan Zhou0Dongfang Yang1Jieyu Liu2Weibo Xu3Xiong Qiu4Yongfei Li5Xi’an Research Institute of Hi-Tech, Xi’an 710025, ChinaXi’an Research Institute of Hi-Tech, Xi’an 710025, ChinaXi’an Research Institute of Hi-Tech, Xi’an 710025, ChinaXi’an Research Institute of Hi-Tech, Xi’an 710025, ChinaXi’an Research Institute of Hi-Tech, Xi’an 710025, ChinaXi’an Research Institute of Hi-Tech, Xi’an 710025, ChinaVisual geolocalization for aerial vehicles based on an analysis of Earth observation imagery is an effective method in GNSS-denied environments. However, existing methods for geographic location estimation have limitations: one relies on high-precision geodetic elevation data, which is costly, and the other assumes a flat ground surface, ignoring elevation differences. This paper presents a novel aerial vehicle geolocalization method. It integrates 2D information and relative depth information, which are both from Earth observation images. Firstly, the aerial and reference remote sensing satellite images are fed into a feature-matching network to extract pixel-level feature-matching pairs. Then, a depth estimation network is used to estimate the relative depth of the satellite remote sensing image, thereby obtaining the relative depth information of the ground area within the field of view of the aerial image. Finally, high-confidence matching pairs with similar depth and uniform distribution are selected to estimate the geographic location of the aerial vehicle. Experimental results demonstrate that the proposed method outperforms existing ones in terms of geolocalization accuracy and stability. It eliminates reliance on elevation data or planar assumptions, thus providing a more adaptable and robust solution for aerial vehicle geolocalization in GNSS-denied environments.https://www.mdpi.com/2072-4292/17/13/2291GNSS-denied environmentsaerial vehicle visual geolocalizationsatellite remote sensing imagerelative depth estimationgeographic location estimation |
| spellingShingle | Maoan Zhou Dongfang Yang Jieyu Liu Weibo Xu Xiong Qiu Yongfei Li Visual Geolocalization for Aerial Vehicles via Fusion of Satellite Remote Sensing Imagery and Its Relative Depth Information Remote Sensing GNSS-denied environments aerial vehicle visual geolocalization satellite remote sensing image relative depth estimation geographic location estimation |
| title | Visual Geolocalization for Aerial Vehicles via Fusion of Satellite Remote Sensing Imagery and Its Relative Depth Information |
| title_full | Visual Geolocalization for Aerial Vehicles via Fusion of Satellite Remote Sensing Imagery and Its Relative Depth Information |
| title_fullStr | Visual Geolocalization for Aerial Vehicles via Fusion of Satellite Remote Sensing Imagery and Its Relative Depth Information |
| title_full_unstemmed | Visual Geolocalization for Aerial Vehicles via Fusion of Satellite Remote Sensing Imagery and Its Relative Depth Information |
| title_short | Visual Geolocalization for Aerial Vehicles via Fusion of Satellite Remote Sensing Imagery and Its Relative Depth Information |
| title_sort | visual geolocalization for aerial vehicles via fusion of satellite remote sensing imagery and its relative depth information |
| topic | GNSS-denied environments aerial vehicle visual geolocalization satellite remote sensing image relative depth estimation geographic location estimation |
| url | https://www.mdpi.com/2072-4292/17/13/2291 |
| work_keys_str_mv | AT maoanzhou visualgeolocalizationforaerialvehiclesviafusionofsatelliteremotesensingimageryanditsrelativedepthinformation AT dongfangyang visualgeolocalizationforaerialvehiclesviafusionofsatelliteremotesensingimageryanditsrelativedepthinformation AT jieyuliu visualgeolocalizationforaerialvehiclesviafusionofsatelliteremotesensingimageryanditsrelativedepthinformation AT weiboxu visualgeolocalizationforaerialvehiclesviafusionofsatelliteremotesensingimageryanditsrelativedepthinformation AT xiongqiu visualgeolocalizationforaerialvehiclesviafusionofsatelliteremotesensingimageryanditsrelativedepthinformation AT yongfeili visualgeolocalizationforaerialvehiclesviafusionofsatelliteremotesensingimageryanditsrelativedepthinformation |