A Fast and Robust Heterologous Image Matching Method for Visual Geo-Localization of Low-Altitude UAVs
Visual geo-localization can achieve UAVs (Unmanned Aerial Vehicles) position during GNSS (Global Navigation Satellite System) denial or restriction. However, The performance of visual geo-localization is seriously impaired by illumination variation, different scales, viewpoint difference, spare text...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/22/5879 |
| _version_ | 1797464035317252096 |
|---|---|
| author | Haigang Sui Jiajie Li Junfeng Lei Chang Liu Guohua Gou |
| author_facet | Haigang Sui Jiajie Li Junfeng Lei Chang Liu Guohua Gou |
| author_sort | Haigang Sui |
| collection | DOAJ |
| description | Visual geo-localization can achieve UAVs (Unmanned Aerial Vehicles) position during GNSS (Global Navigation Satellite System) denial or restriction. However, The performance of visual geo-localization is seriously impaired by illumination variation, different scales, viewpoint difference, spare texture, and computer power of UAVs, etc. In this paper, a fast detector-free two-stage matching method is proposed to improve the visual geo-localization of low-altitude UAVs. A detector-free matching method and perspective transformation module are incorporated into the coarse and fine matching stages to improve the robustness of the weak texture and viewpoint data. The minimum Euclidean distance is used to accelerate the coarse matching, and the coordinate regression based on DSNT (Differentiable Spatial to Numerical) transform is used to improve the fine matching accuracy respectively. The experimental results show that the average localization precision of the proposed method is 2.24 m, which is 0.33 m higher than that of the current typical matching methods. In addition, this method has obvious advantages in localization robustness and inference efficiency on Jetson Xavier NX, which completed to match and localize all images in the dataset while the localization frequency reached the best. |
| first_indexed | 2024-03-09T18:02:14Z |
| format | Article |
| id | doaj.art-a0b75018d05747c099b1b2eec649f6b7 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T18:02:14Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-a0b75018d05747c099b1b2eec649f6b72023-11-24T09:51:56ZengMDPI AGRemote Sensing2072-42922022-11-011422587910.3390/rs14225879A Fast and Robust Heterologous Image Matching Method for Visual Geo-Localization of Low-Altitude UAVsHaigang Sui0Jiajie Li1Junfeng Lei2Chang Liu3Guohua Gou4State Key Laboratory Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430070, ChinaState Key Laboratory Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430070, ChinaElectronic Information School, Wuhan University, Wuhan 430070, ChinaState Key Laboratory Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430070, ChinaState Key Laboratory Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430070, ChinaVisual geo-localization can achieve UAVs (Unmanned Aerial Vehicles) position during GNSS (Global Navigation Satellite System) denial or restriction. However, The performance of visual geo-localization is seriously impaired by illumination variation, different scales, viewpoint difference, spare texture, and computer power of UAVs, etc. In this paper, a fast detector-free two-stage matching method is proposed to improve the visual geo-localization of low-altitude UAVs. A detector-free matching method and perspective transformation module are incorporated into the coarse and fine matching stages to improve the robustness of the weak texture and viewpoint data. The minimum Euclidean distance is used to accelerate the coarse matching, and the coordinate regression based on DSNT (Differentiable Spatial to Numerical) transform is used to improve the fine matching accuracy respectively. The experimental results show that the average localization precision of the proposed method is 2.24 m, which is 0.33 m higher than that of the current typical matching methods. In addition, this method has obvious advantages in localization robustness and inference efficiency on Jetson Xavier NX, which completed to match and localize all images in the dataset while the localization frequency reached the best.https://www.mdpi.com/2072-4292/14/22/5879UAVsvisual geo-localizationimage matchingdetector-freeperspective transformation |
| spellingShingle | Haigang Sui Jiajie Li Junfeng Lei Chang Liu Guohua Gou A Fast and Robust Heterologous Image Matching Method for Visual Geo-Localization of Low-Altitude UAVs Remote Sensing UAVs visual geo-localization image matching detector-free perspective transformation |
| title | A Fast and Robust Heterologous Image Matching Method for Visual Geo-Localization of Low-Altitude UAVs |
| title_full | A Fast and Robust Heterologous Image Matching Method for Visual Geo-Localization of Low-Altitude UAVs |
| title_fullStr | A Fast and Robust Heterologous Image Matching Method for Visual Geo-Localization of Low-Altitude UAVs |
| title_full_unstemmed | A Fast and Robust Heterologous Image Matching Method for Visual Geo-Localization of Low-Altitude UAVs |
| title_short | A Fast and Robust Heterologous Image Matching Method for Visual Geo-Localization of Low-Altitude UAVs |
| title_sort | fast and robust heterologous image matching method for visual geo localization of low altitude uavs |
| topic | UAVs visual geo-localization image matching detector-free perspective transformation |
| url | https://www.mdpi.com/2072-4292/14/22/5879 |
| work_keys_str_mv | AT haigangsui afastandrobustheterologousimagematchingmethodforvisualgeolocalizationoflowaltitudeuavs AT jiajieli afastandrobustheterologousimagematchingmethodforvisualgeolocalizationoflowaltitudeuavs AT junfenglei afastandrobustheterologousimagematchingmethodforvisualgeolocalizationoflowaltitudeuavs AT changliu afastandrobustheterologousimagematchingmethodforvisualgeolocalizationoflowaltitudeuavs AT guohuagou afastandrobustheterologousimagematchingmethodforvisualgeolocalizationoflowaltitudeuavs AT haigangsui fastandrobustheterologousimagematchingmethodforvisualgeolocalizationoflowaltitudeuavs AT jiajieli fastandrobustheterologousimagematchingmethodforvisualgeolocalizationoflowaltitudeuavs AT junfenglei fastandrobustheterologousimagematchingmethodforvisualgeolocalizationoflowaltitudeuavs AT changliu fastandrobustheterologousimagematchingmethodforvisualgeolocalizationoflowaltitudeuavs AT guohuagou fastandrobustheterologousimagematchingmethodforvisualgeolocalizationoflowaltitudeuavs |