Detection of Military Targets on Ground and Sea by UAVs with Low-Altitude Oblique Perspective
Small-scale low-altitude unmanned aerial vehicles (UAVs) equipped with perception capability for military targets will become increasingly essential for strategic reconnaissance and stationary patrols in the future. To respond to challenges such as complex terrain and weather variations, as well as...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/7/1288 |
| _version_ | 1797212015210528768 |
|---|---|
| author | Bohan Zeng Shan Gao Yuelei Xu Zhaoxiang Zhang Fan Li Chenghang Wang |
| author_facet | Bohan Zeng Shan Gao Yuelei Xu Zhaoxiang Zhang Fan Li Chenghang Wang |
| author_sort | Bohan Zeng |
| collection | DOAJ |
| description | Small-scale low-altitude unmanned aerial vehicles (UAVs) equipped with perception capability for military targets will become increasingly essential for strategic reconnaissance and stationary patrols in the future. To respond to challenges such as complex terrain and weather variations, as well as the deception and camouflage of military targets, this paper proposes a hybrid detection model that combines Convolutional Neural Network (CNN) and Transformer architecture in a decoupled manner. The proposed detector consists of the C-branch and the T-branch. In the C-branch, Multi-gradient Path Network (MgpNet) is introduced, inspired by the multi-gradient flow strategy, excelling in capturing the local feature information of an image. In the T-branch, RPFormer, a Region–Pixel two-stage attention mechanism, is proposed to aggregate the global feature information of the whole image. A feature fusion strategy is proposed to merge the feature layers of the two branches, further improving the detection accuracy. Furthermore, to better simulate real UAVs’ reconnaissance environments, we construct a dataset of military targets in complex environments captured from an oblique perspective to evaluate the proposed detector. In ablation experiments, different fusion methods are validated, and the results demonstrate the effectiveness of the proposed fusion strategy. In comparative experiments, the proposed detector outperforms most advanced general detectors. |
| first_indexed | 2024-04-24T10:35:40Z |
| format | Article |
| id | doaj.art-77693ae4cd1349119bf943fbe5c3357f |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-04-24T10:35:40Z |
| publishDate | 2024-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-77693ae4cd1349119bf943fbe5c3357f2024-04-12T13:25:54ZengMDPI AGRemote Sensing2072-42922024-04-01167128810.3390/rs16071288Detection of Military Targets on Ground and Sea by UAVs with Low-Altitude Oblique PerspectiveBohan Zeng0Shan Gao1Yuelei Xu2Zhaoxiang Zhang3Fan Li4Chenghang Wang5Unmanned System Research Institute, Northwestern Polytechnical University, Xi’an 710129, ChinaWuhan National Laboratory for Optoelectronics, Huazhong Institute of Electro-Optics, Wuhan 430073, ChinaUnmanned System Research Institute, Northwestern Polytechnical University, Xi’an 710129, ChinaUnmanned System Research Institute, Northwestern Polytechnical University, Xi’an 710129, ChinaUnmanned System Research Institute, Northwestern Polytechnical University, Xi’an 710129, ChinaUnmanned System Research Institute, Northwestern Polytechnical University, Xi’an 710129, ChinaSmall-scale low-altitude unmanned aerial vehicles (UAVs) equipped with perception capability for military targets will become increasingly essential for strategic reconnaissance and stationary patrols in the future. To respond to challenges such as complex terrain and weather variations, as well as the deception and camouflage of military targets, this paper proposes a hybrid detection model that combines Convolutional Neural Network (CNN) and Transformer architecture in a decoupled manner. The proposed detector consists of the C-branch and the T-branch. In the C-branch, Multi-gradient Path Network (MgpNet) is introduced, inspired by the multi-gradient flow strategy, excelling in capturing the local feature information of an image. In the T-branch, RPFormer, a Region–Pixel two-stage attention mechanism, is proposed to aggregate the global feature information of the whole image. A feature fusion strategy is proposed to merge the feature layers of the two branches, further improving the detection accuracy. Furthermore, to better simulate real UAVs’ reconnaissance environments, we construct a dataset of military targets in complex environments captured from an oblique perspective to evaluate the proposed detector. In ablation experiments, different fusion methods are validated, and the results demonstrate the effectiveness of the proposed fusion strategy. In comparative experiments, the proposed detector outperforms most advanced general detectors.https://www.mdpi.com/2072-4292/16/7/1288unmanned aerial vehicle (UAV)object detectionmilitary targetsfeature fusion strategyhybrid detection model |
| spellingShingle | Bohan Zeng Shan Gao Yuelei Xu Zhaoxiang Zhang Fan Li Chenghang Wang Detection of Military Targets on Ground and Sea by UAVs with Low-Altitude Oblique Perspective Remote Sensing unmanned aerial vehicle (UAV) object detection military targets feature fusion strategy hybrid detection model |
| title | Detection of Military Targets on Ground and Sea by UAVs with Low-Altitude Oblique Perspective |
| title_full | Detection of Military Targets on Ground and Sea by UAVs with Low-Altitude Oblique Perspective |
| title_fullStr | Detection of Military Targets on Ground and Sea by UAVs with Low-Altitude Oblique Perspective |
| title_full_unstemmed | Detection of Military Targets on Ground and Sea by UAVs with Low-Altitude Oblique Perspective |
| title_short | Detection of Military Targets on Ground and Sea by UAVs with Low-Altitude Oblique Perspective |
| title_sort | detection of military targets on ground and sea by uavs with low altitude oblique perspective |
| topic | unmanned aerial vehicle (UAV) object detection military targets feature fusion strategy hybrid detection model |
| url | https://www.mdpi.com/2072-4292/16/7/1288 |
| work_keys_str_mv | AT bohanzeng detectionofmilitarytargetsongroundandseabyuavswithlowaltitudeobliqueperspective AT shangao detectionofmilitarytargetsongroundandseabyuavswithlowaltitudeobliqueperspective AT yueleixu detectionofmilitarytargetsongroundandseabyuavswithlowaltitudeobliqueperspective AT zhaoxiangzhang detectionofmilitarytargetsongroundandseabyuavswithlowaltitudeobliqueperspective AT fanli detectionofmilitarytargetsongroundandseabyuavswithlowaltitudeobliqueperspective AT chenghangwang detectionofmilitarytargetsongroundandseabyuavswithlowaltitudeobliqueperspective |