A Faster and More Effective Cross-View Matching Method of UAV and Satellite Images for UAV Geolocalization
Cross-view geolocalization matches the same target in different images from various views, such as views of unmanned aerial vehicles (UAVs) and satellites, which is a key technology for UAVs to autonomously locate and navigate without a positioning system (e.g., GPS and GNSS). The most challenging a...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/19/3979 |
| _version_ | 1797515763325599744 |
|---|---|
| author | Jiedong Zhuang Ming Dai Xuruoyan Chen Enhui Zheng |
| author_facet | Jiedong Zhuang Ming Dai Xuruoyan Chen Enhui Zheng |
| author_sort | Jiedong Zhuang |
| collection | DOAJ |
| description | Cross-view geolocalization matches the same target in different images from various views, such as views of unmanned aerial vehicles (UAVs) and satellites, which is a key technology for UAVs to autonomously locate and navigate without a positioning system (e.g., GPS and GNSS). The most challenging aspect in this area is the shifting of targets and nonuniform scales among different views. Published methods focus on extracting coarse features from parts of images, but neglect the relationship between different views, and the influence of scale and shifting. To bridge this gap, an effective network is proposed with well-designed structures, referred to as multiscale block attention (MSBA), based on a local pattern network. MSBA cuts images into several parts with different scales, among which self-attention is applied to make feature extraction more efficient. The features of different views are extracted by a multibranch structure, which was designed to make different branches learn from each other, leading to a more subtle relationship between views. The method was implemented with the newest UAV-based geolocalization dataset. Compared with the existing state-of-the-art (SOTA) method, MSBA accuracy improved by almost 10% when the inference time was equal to that of the SOTA method; when the accuracy of MSBA was the same as that of the SOTA method, inference time was shortened by 30%. |
| first_indexed | 2024-03-10T06:51:53Z |
| format | Article |
| id | doaj.art-2f940a7cf2d04f7987238580ce6e2dfe |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T06:51:53Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-2f940a7cf2d04f7987238580ce6e2dfe2023-11-22T16:43:41ZengMDPI AGRemote Sensing2072-42922021-10-011319397910.3390/rs13193979A Faster and More Effective Cross-View Matching Method of UAV and Satellite Images for UAV GeolocalizationJiedong Zhuang0Ming Dai1Xuruoyan Chen2Enhui Zheng3Unmanned System Application Technology Research Institute, China Jiliang University, Hangzhou 310018, ChinaUnmanned System Application Technology Research Institute, China Jiliang University, Hangzhou 310018, ChinaUnmanned System Application Technology Research Institute, China Jiliang University, Hangzhou 310018, ChinaUnmanned System Application Technology Research Institute, China Jiliang University, Hangzhou 310018, ChinaCross-view geolocalization matches the same target in different images from various views, such as views of unmanned aerial vehicles (UAVs) and satellites, which is a key technology for UAVs to autonomously locate and navigate without a positioning system (e.g., GPS and GNSS). The most challenging aspect in this area is the shifting of targets and nonuniform scales among different views. Published methods focus on extracting coarse features from parts of images, but neglect the relationship between different views, and the influence of scale and shifting. To bridge this gap, an effective network is proposed with well-designed structures, referred to as multiscale block attention (MSBA), based on a local pattern network. MSBA cuts images into several parts with different scales, among which self-attention is applied to make feature extraction more efficient. The features of different views are extracted by a multibranch structure, which was designed to make different branches learn from each other, leading to a more subtle relationship between views. The method was implemented with the newest UAV-based geolocalization dataset. Compared with the existing state-of-the-art (SOTA) method, MSBA accuracy improved by almost 10% when the inference time was equal to that of the SOTA method; when the accuracy of MSBA was the same as that of the SOTA method, inference time was shortened by 30%.https://www.mdpi.com/2072-4292/13/19/3979cross-view image matchinggeolocalizationUAV image localizationdeep neural network |
| spellingShingle | Jiedong Zhuang Ming Dai Xuruoyan Chen Enhui Zheng A Faster and More Effective Cross-View Matching Method of UAV and Satellite Images for UAV Geolocalization Remote Sensing cross-view image matching geolocalization UAV image localization deep neural network |
| title | A Faster and More Effective Cross-View Matching Method of UAV and Satellite Images for UAV Geolocalization |
| title_full | A Faster and More Effective Cross-View Matching Method of UAV and Satellite Images for UAV Geolocalization |
| title_fullStr | A Faster and More Effective Cross-View Matching Method of UAV and Satellite Images for UAV Geolocalization |
| title_full_unstemmed | A Faster and More Effective Cross-View Matching Method of UAV and Satellite Images for UAV Geolocalization |
| title_short | A Faster and More Effective Cross-View Matching Method of UAV and Satellite Images for UAV Geolocalization |
| title_sort | faster and more effective cross view matching method of uav and satellite images for uav geolocalization |
| topic | cross-view image matching geolocalization UAV image localization deep neural network |
| url | https://www.mdpi.com/2072-4292/13/19/3979 |
| work_keys_str_mv | AT jiedongzhuang afasterandmoreeffectivecrossviewmatchingmethodofuavandsatelliteimagesforuavgeolocalization AT mingdai afasterandmoreeffectivecrossviewmatchingmethodofuavandsatelliteimagesforuavgeolocalization AT xuruoyanchen afasterandmoreeffectivecrossviewmatchingmethodofuavandsatelliteimagesforuavgeolocalization AT enhuizheng afasterandmoreeffectivecrossviewmatchingmethodofuavandsatelliteimagesforuavgeolocalization AT jiedongzhuang fasterandmoreeffectivecrossviewmatchingmethodofuavandsatelliteimagesforuavgeolocalization AT mingdai fasterandmoreeffectivecrossviewmatchingmethodofuavandsatelliteimagesforuavgeolocalization AT xuruoyanchen fasterandmoreeffectivecrossviewmatchingmethodofuavandsatelliteimagesforuavgeolocalization AT enhuizheng fasterandmoreeffectivecrossviewmatchingmethodofuavandsatelliteimagesforuavgeolocalization |