SVDD: SAR Vehicle Dataset Construction and Detection
With the advent of high-quality SAR images and the rapid development of computing technology, the object detection algorithms based on convolution neural network have attracted a lot of attention in the field of SAR object detection. At present, the main dataset for SAR target detection in China foc...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10848068/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576767544524800 |
|---|---|
| author | Dan Gao Xiaofang Wu Zhijin Wen Yue Xu Zhengchao Chen |
| author_facet | Dan Gao Xiaofang Wu Zhijin Wen Yue Xu Zhengchao Chen |
| author_sort | Dan Gao |
| collection | DOAJ |
| description | With the advent of high-quality SAR images and the rapid development of computing technology, the object detection algorithms based on convolution neural network have attracted a lot of attention in the field of SAR object detection. At present, the main dataset for SAR target detection in China focus on ships, there is a lack of SAR vehicle detect datasets, and complex ground scenes can affect vehicle detection performance. To solve these problems, we proposed a lightweight SAR vehicle detection algorithm, aiming to improve the vehicle detection accuracy and simplify the model complexity. First, we constructed a multi-band SAR vehicle detection dataset (SVDD) with annotations as the training dataset of the object detection model. Then, we introduced dual conv into the RT-DETR model. Dual conv uses group convolution technology to filter the convolutional network to reduce model parameters, so we can achieve a lightweight and real-time end-to-end detection. Finally, we used the mmdetection framework as a benchmark and test the robust performance under different conditions. Experimental results show that the AP50 of we proposed method reaches 98.5%, achieving excellent detection performance. |
| format | Article |
| id | doaj-art-848854a837704e178b55eeba99a322fc |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-848854a837704e178b55eeba99a322fc2025-01-31T00:01:07ZengIEEEIEEE Access2169-35362025-01-0113181071812210.1109/ACCESS.2025.353229410848068SVDD: SAR Vehicle Dataset Construction and DetectionDan Gao0https://orcid.org/0009-0003-1207-9350Xiaofang Wu1https://orcid.org/0009-0005-2525-4183Zhijin Wen2Yue Xu3https://orcid.org/0000-0001-6683-2107Zhengchao Chen4https://orcid.org/0000-0003-4293-6459Academy of Military Sciences of the People’s Liberation Army, Institute of Systems Engineering, Beijing, ChinaAcademy of Military Sciences of the People’s Liberation Army, Institute of Systems Engineering, Beijing, ChinaAcademy of Military Sciences of the People’s Liberation Army, Institute of Systems Engineering, Beijing, ChinaKey Laboratory of Remote Sensing and Digital Earth, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Remote Sensing and Digital Earth, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaWith the advent of high-quality SAR images and the rapid development of computing technology, the object detection algorithms based on convolution neural network have attracted a lot of attention in the field of SAR object detection. At present, the main dataset for SAR target detection in China focus on ships, there is a lack of SAR vehicle detect datasets, and complex ground scenes can affect vehicle detection performance. To solve these problems, we proposed a lightweight SAR vehicle detection algorithm, aiming to improve the vehicle detection accuracy and simplify the model complexity. First, we constructed a multi-band SAR vehicle detection dataset (SVDD) with annotations as the training dataset of the object detection model. Then, we introduced dual conv into the RT-DETR model. Dual conv uses group convolution technology to filter the convolutional network to reduce model parameters, so we can achieve a lightweight and real-time end-to-end detection. Finally, we used the mmdetection framework as a benchmark and test the robust performance under different conditions. Experimental results show that the AP50 of we proposed method reaches 98.5%, achieving excellent detection performance.https://ieeexplore.ieee.org/document/10848068/Deep learningobject detectionsynthetic aperture radar datasetsvision transformer |
| spellingShingle | Dan Gao Xiaofang Wu Zhijin Wen Yue Xu Zhengchao Chen SVDD: SAR Vehicle Dataset Construction and Detection IEEE Access Deep learning object detection synthetic aperture radar datasets vision transformer |
| title | SVDD: SAR Vehicle Dataset Construction and Detection |
| title_full | SVDD: SAR Vehicle Dataset Construction and Detection |
| title_fullStr | SVDD: SAR Vehicle Dataset Construction and Detection |
| title_full_unstemmed | SVDD: SAR Vehicle Dataset Construction and Detection |
| title_short | SVDD: SAR Vehicle Dataset Construction and Detection |
| title_sort | svdd sar vehicle dataset construction and detection |
| topic | Deep learning object detection synthetic aperture radar datasets vision transformer |
| url | https://ieeexplore.ieee.org/document/10848068/ |
| work_keys_str_mv | AT dangao svddsarvehicledatasetconstructionanddetection AT xiaofangwu svddsarvehicledatasetconstructionanddetection AT zhijinwen svddsarvehicledatasetconstructionanddetection AT yuexu svddsarvehicledatasetconstructionanddetection AT zhengchaochen svddsarvehicledatasetconstructionanddetection |