A Semantic Guidance and Transformer-Based Matching Method for UAVs and Satellite Images for UAV Geo-Localization
It is a challenging task for unmanned aerial vehicles (UAVs) without a positioning system to locate targets by using images. Matching drone and satellite images is one of the key steps in this task. Due to the large angle and scale gap between drone and satellite views, it is very important to extra...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9743475/ |
| _version_ | 1818749635474227200 |
|---|---|
| author | Jiedong Zhuang Xuruoyan Chen Ming Dai Wenbo Lan Yongheng Cai Enhui Zheng |
| author_facet | Jiedong Zhuang Xuruoyan Chen Ming Dai Wenbo Lan Yongheng Cai Enhui Zheng |
| author_sort | Jiedong Zhuang |
| collection | DOAJ |
| description | It is a challenging task for unmanned aerial vehicles (UAVs) without a positioning system to locate targets by using images. Matching drone and satellite images is one of the key steps in this task. Due to the large angle and scale gap between drone and satellite views, it is very important to extract fine-grained features with strong characterization ability. Most of the published methods are based on the CNN structure, but a lot of information will be lost when using such methods. This is caused by the limitations of the convolution operation (e.g. limited receptive field and downsampling operation). To make up for this shortcoming, a transformer-based network is proposed to extract more contextual information. The network promotes feature alignment through semantic guidance module (SGM). SGM aligns the same semantic parts in the two images by classifying each pixel in the images based on the attention of pixels. In addition, this method can be easily combined with existing methods. The proposed method has been implemented with the newest UAV-based geo-localization dataset. Compared with the existing state-of-the-art (SOTA) method, the proposed method achieves almost 8% improvement in accuracy. |
| first_indexed | 2024-12-18T04:06:55Z |
| format | Article |
| id | doaj.art-1d96c187a9b249ed911d931e1f66a28b |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-18T04:06:55Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-1d96c187a9b249ed911d931e1f66a28b2022-12-21T21:21:35ZengIEEEIEEE Access2169-35362022-01-0110342773428710.1109/ACCESS.2022.31626939743475A Semantic Guidance and Transformer-Based Matching Method for UAVs and Satellite Images for UAV Geo-LocalizationJiedong Zhuang0https://orcid.org/0000-0003-0551-5911Xuruoyan Chen1Ming Dai2Wenbo Lan3Yongheng Cai4Enhui Zheng5https://orcid.org/0000-0002-1358-7846Unmanned System Application Technology Research Institute, China Jiliang University, Hangzhou, ChinaUnmanned System Application Technology Research Institute, China Jiliang University, Hangzhou, ChinaUnmanned System Application Technology Research Institute, China Jiliang University, Hangzhou, ChinaChina Academy of Aerospace Aerodynamics (CAAA), Beijing, ChinaChina Academy of Aerospace Aerodynamics (CAAA), Beijing, ChinaUnmanned System Application Technology Research Institute, China Jiliang University, Hangzhou, ChinaIt is a challenging task for unmanned aerial vehicles (UAVs) without a positioning system to locate targets by using images. Matching drone and satellite images is one of the key steps in this task. Due to the large angle and scale gap between drone and satellite views, it is very important to extract fine-grained features with strong characterization ability. Most of the published methods are based on the CNN structure, but a lot of information will be lost when using such methods. This is caused by the limitations of the convolution operation (e.g. limited receptive field and downsampling operation). To make up for this shortcoming, a transformer-based network is proposed to extract more contextual information. The network promotes feature alignment through semantic guidance module (SGM). SGM aligns the same semantic parts in the two images by classifying each pixel in the images based on the attention of pixels. In addition, this method can be easily combined with existing methods. The proposed method has been implemented with the newest UAV-based geo-localization dataset. Compared with the existing state-of-the-art (SOTA) method, the proposed method achieves almost 8% improvement in accuracy.https://ieeexplore.ieee.org/document/9743475/Cross-view image matchinggeo-localizationUAV image localizationdeep neural network |
| spellingShingle | Jiedong Zhuang Xuruoyan Chen Ming Dai Wenbo Lan Yongheng Cai Enhui Zheng A Semantic Guidance and Transformer-Based Matching Method for UAVs and Satellite Images for UAV Geo-Localization IEEE Access Cross-view image matching geo-localization UAV image localization deep neural network |
| title | A Semantic Guidance and Transformer-Based Matching Method for UAVs and Satellite Images for UAV Geo-Localization |
| title_full | A Semantic Guidance and Transformer-Based Matching Method for UAVs and Satellite Images for UAV Geo-Localization |
| title_fullStr | A Semantic Guidance and Transformer-Based Matching Method for UAVs and Satellite Images for UAV Geo-Localization |
| title_full_unstemmed | A Semantic Guidance and Transformer-Based Matching Method for UAVs and Satellite Images for UAV Geo-Localization |
| title_short | A Semantic Guidance and Transformer-Based Matching Method for UAVs and Satellite Images for UAV Geo-Localization |
| title_sort | semantic guidance and transformer based matching method for uavs and satellite images for uav geo localization |
| topic | Cross-view image matching geo-localization UAV image localization deep neural network |
| url | https://ieeexplore.ieee.org/document/9743475/ |
| work_keys_str_mv | AT jiedongzhuang asemanticguidanceandtransformerbasedmatchingmethodforuavsandsatelliteimagesforuavgeolocalization AT xuruoyanchen asemanticguidanceandtransformerbasedmatchingmethodforuavsandsatelliteimagesforuavgeolocalization AT mingdai asemanticguidanceandtransformerbasedmatchingmethodforuavsandsatelliteimagesforuavgeolocalization AT wenbolan asemanticguidanceandtransformerbasedmatchingmethodforuavsandsatelliteimagesforuavgeolocalization AT yonghengcai asemanticguidanceandtransformerbasedmatchingmethodforuavsandsatelliteimagesforuavgeolocalization AT enhuizheng asemanticguidanceandtransformerbasedmatchingmethodforuavsandsatelliteimagesforuavgeolocalization AT jiedongzhuang semanticguidanceandtransformerbasedmatchingmethodforuavsandsatelliteimagesforuavgeolocalization AT xuruoyanchen semanticguidanceandtransformerbasedmatchingmethodforuavsandsatelliteimagesforuavgeolocalization AT mingdai semanticguidanceandtransformerbasedmatchingmethodforuavsandsatelliteimagesforuavgeolocalization AT wenbolan semanticguidanceandtransformerbasedmatchingmethodforuavsandsatelliteimagesforuavgeolocalization AT yonghengcai semanticguidanceandtransformerbasedmatchingmethodforuavsandsatelliteimagesforuavgeolocalization AT enhuizheng semanticguidanceandtransformerbasedmatchingmethodforuavsandsatelliteimagesforuavgeolocalization |