An Efficient Pyramid Transformer Network for Cross-View Geo-Localization in Complex Terrains
Unmanned aerial vehicle (UAV) self-localization in complex environments is critical when global navigation satellite systems (GNSSs) are unreliable. Existing datasets, often limited to low-altitude urban scenes, hinder generalization. This study introduces Multi-UAV, a novel dataset with 17.4 k high...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/9/5/379 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850127137503182848 |
|---|---|
| author | Chengjie Ju Wangping Xu Nanxing Chen Enhui Zheng |
| author_facet | Chengjie Ju Wangping Xu Nanxing Chen Enhui Zheng |
| author_sort | Chengjie Ju |
| collection | DOAJ |
| description | Unmanned aerial vehicle (UAV) self-localization in complex environments is critical when global navigation satellite systems (GNSSs) are unreliable. Existing datasets, often limited to low-altitude urban scenes, hinder generalization. This study introduces Multi-UAV, a novel dataset with 17.4 k high-resolution UAV–satellite image pairs from diverse terrains (urban, rural, mountainous, farmland, coastal) and altitudes across China, enhancing cross-view geolocalization research. We propose a lightweight value reduction pyramid transformer (VRPT) for efficient feature extraction and a residual feature pyramid network (RFPN) for multi-scale feature fusion. Using meter-level accuracy (MA@K) and relative distance score (RDS), VRPT achieves robust, high-precision localization across varied terrains, offering significant potential for resource-constrained UAV deployment. |
| format | Article |
| id | doaj-art-a6ffaff4677247c9a725744ee36b6bfd |
| institution | OA Journals |
| issn | 2504-446X |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj-art-a6ffaff4677247c9a725744ee36b6bfd2025-08-20T02:33:44ZengMDPI AGDrones2504-446X2025-05-019537910.3390/drones9050379An Efficient Pyramid Transformer Network for Cross-View Geo-Localization in Complex TerrainsChengjie Ju0Wangping Xu1Nanxing Chen2Enhui Zheng3Department of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou 310018, ChinaDepartment of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou 310018, ChinaDepartment of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou 310018, ChinaDepartment of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou 310018, ChinaUnmanned aerial vehicle (UAV) self-localization in complex environments is critical when global navigation satellite systems (GNSSs) are unreliable. Existing datasets, often limited to low-altitude urban scenes, hinder generalization. This study introduces Multi-UAV, a novel dataset with 17.4 k high-resolution UAV–satellite image pairs from diverse terrains (urban, rural, mountainous, farmland, coastal) and altitudes across China, enhancing cross-view geolocalization research. We propose a lightweight value reduction pyramid transformer (VRPT) for efficient feature extraction and a residual feature pyramid network (RFPN) for multi-scale feature fusion. Using meter-level accuracy (MA@K) and relative distance score (RDS), VRPT achieves robust, high-precision localization across varied terrains, offering significant potential for resource-constrained UAV deployment.https://www.mdpi.com/2504-446X/9/5/379unmanned aerial vehiclegeo-localizationtransformer |
| spellingShingle | Chengjie Ju Wangping Xu Nanxing Chen Enhui Zheng An Efficient Pyramid Transformer Network for Cross-View Geo-Localization in Complex Terrains Drones unmanned aerial vehicle geo-localization transformer |
| title | An Efficient Pyramid Transformer Network for Cross-View Geo-Localization in Complex Terrains |
| title_full | An Efficient Pyramid Transformer Network for Cross-View Geo-Localization in Complex Terrains |
| title_fullStr | An Efficient Pyramid Transformer Network for Cross-View Geo-Localization in Complex Terrains |
| title_full_unstemmed | An Efficient Pyramid Transformer Network for Cross-View Geo-Localization in Complex Terrains |
| title_short | An Efficient Pyramid Transformer Network for Cross-View Geo-Localization in Complex Terrains |
| title_sort | efficient pyramid transformer network for cross view geo localization in complex terrains |
| topic | unmanned aerial vehicle geo-localization transformer |
| url | https://www.mdpi.com/2504-446X/9/5/379 |
| work_keys_str_mv | AT chengjieju anefficientpyramidtransformernetworkforcrossviewgeolocalizationincomplexterrains AT wangpingxu anefficientpyramidtransformernetworkforcrossviewgeolocalizationincomplexterrains AT nanxingchen anefficientpyramidtransformernetworkforcrossviewgeolocalizationincomplexterrains AT enhuizheng anefficientpyramidtransformernetworkforcrossviewgeolocalizationincomplexterrains AT chengjieju efficientpyramidtransformernetworkforcrossviewgeolocalizationincomplexterrains AT wangpingxu efficientpyramidtransformernetworkforcrossviewgeolocalizationincomplexterrains AT nanxingchen efficientpyramidtransformernetworkforcrossviewgeolocalizationincomplexterrains AT enhuizheng efficientpyramidtransformernetworkforcrossviewgeolocalizationincomplexterrains |