LSD-Det: A Lightweight Detector for Small Ship Targets in SAR Images
Synthetic Aperture Radar (SAR) plays a vital role in ship safety monitoring and marine environmental protection. However, ship targets in SAR images are often small, have blurred edges, and suffer from strong background interference, making it difficult for traditional detection algorithms to balanc...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11097882/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849336187199684608 |
|---|---|
| author | Zhen Wang Bin Qin Shang Gao |
| author_facet | Zhen Wang Bin Qin Shang Gao |
| author_sort | Zhen Wang |
| collection | DOAJ |
| description | Synthetic Aperture Radar (SAR) plays a vital role in ship safety monitoring and marine environmental protection. However, ship targets in SAR images are often small, have blurred edges, and suffer from strong background interference, making it difficult for traditional detection algorithms to balance accuracy and real-time performance. To address these challenges, this paper proposes LSD-Det, a lightweight SAR ship detection model improved from YOLOv8n. First, the YOLOv8n architecture is streamlined to reduce redundancy, enhancing suitability for SAR detection. Then, a Grouped Split Enhanced Channel Attention (GSECA) module is introduced in the backbone, combining average and max pooling with channel shuffle to improve recognition of small targets and suppress background noise. Additionally, a Global-Enhanced Dilated Wavelet Transform (GEDWT) module is embedded in the neck’s C2f structure to enhance multi-scale feature representation with minimal computational overhead. Furthermore, the original CIoU loss is replaced with PIoUv2, which accelerates convergence and improves bounding box regression accuracy. Experiments conducted on two publicly available SAR ship detection datasets, SSDD and HRSID, demonstrate that LSD-Det significantly reduces computational cost while maintaining high detection performance. Specifically, parameters are reduced by 65.7%, GFLOPs by 20.7%, and inference speed is notably improved. LSD-Det also improves mAP on SSDD by 1.2% (mAP@0.5) and 2.2% (mAP@0.5:0.95), with corresponding gains of 0.8% and 1.3% on HRSID. The experimental outcomes demonstrate that the proposed approach maintains a desirable trade-off between precision and computational efficiency, making it suitable for real-time SAR ship detection under limited-resource conditions. |
| format | Article |
| id | doaj-art-41cbc098e6864d249e3b4513c6b26c95 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-41cbc098e6864d249e3b4513c6b26c952025-08-20T03:45:03ZengIEEEIEEE Access2169-35362025-01-011313348313349610.1109/ACCESS.2025.359302111097882LSD-Det: A Lightweight Detector for Small Ship Targets in SAR ImagesZhen Wang0https://orcid.org/0009-0005-8132-393XBin Qin1https://orcid.org/0000-0002-9636-9536Shang Gao2https://orcid.org/0000-0001-5750-1680School of Computer, Jiangsu University of Science and Technology, Zhenjiang, ChinaSchool of Computer, Jiangsu University of Science and Technology, Zhenjiang, ChinaSchool of Computer, Jiangsu University of Science and Technology, Zhenjiang, ChinaSynthetic Aperture Radar (SAR) plays a vital role in ship safety monitoring and marine environmental protection. However, ship targets in SAR images are often small, have blurred edges, and suffer from strong background interference, making it difficult for traditional detection algorithms to balance accuracy and real-time performance. To address these challenges, this paper proposes LSD-Det, a lightweight SAR ship detection model improved from YOLOv8n. First, the YOLOv8n architecture is streamlined to reduce redundancy, enhancing suitability for SAR detection. Then, a Grouped Split Enhanced Channel Attention (GSECA) module is introduced in the backbone, combining average and max pooling with channel shuffle to improve recognition of small targets and suppress background noise. Additionally, a Global-Enhanced Dilated Wavelet Transform (GEDWT) module is embedded in the neck’s C2f structure to enhance multi-scale feature representation with minimal computational overhead. Furthermore, the original CIoU loss is replaced with PIoUv2, which accelerates convergence and improves bounding box regression accuracy. Experiments conducted on two publicly available SAR ship detection datasets, SSDD and HRSID, demonstrate that LSD-Det significantly reduces computational cost while maintaining high detection performance. Specifically, parameters are reduced by 65.7%, GFLOPs by 20.7%, and inference speed is notably improved. LSD-Det also improves mAP on SSDD by 1.2% (mAP@0.5) and 2.2% (mAP@0.5:0.95), with corresponding gains of 0.8% and 1.3% on HRSID. The experimental outcomes demonstrate that the proposed approach maintains a desirable trade-off between precision and computational efficiency, making it suitable for real-time SAR ship detection under limited-resource conditions.https://ieeexplore.ieee.org/document/11097882/Lightweightship detectionsynthetic aperture radarYOLOv8 |
| spellingShingle | Zhen Wang Bin Qin Shang Gao LSD-Det: A Lightweight Detector for Small Ship Targets in SAR Images IEEE Access Lightweight ship detection synthetic aperture radar YOLOv8 |
| title | LSD-Det: A Lightweight Detector for Small Ship Targets in SAR Images |
| title_full | LSD-Det: A Lightweight Detector for Small Ship Targets in SAR Images |
| title_fullStr | LSD-Det: A Lightweight Detector for Small Ship Targets in SAR Images |
| title_full_unstemmed | LSD-Det: A Lightweight Detector for Small Ship Targets in SAR Images |
| title_short | LSD-Det: A Lightweight Detector for Small Ship Targets in SAR Images |
| title_sort | lsd det a lightweight detector for small ship targets in sar images |
| topic | Lightweight ship detection synthetic aperture radar YOLOv8 |
| url | https://ieeexplore.ieee.org/document/11097882/ |
| work_keys_str_mv | AT zhenwang lsddetalightweightdetectorforsmallshiptargetsinsarimages AT binqin lsddetalightweightdetectorforsmallshiptargetsinsarimages AT shanggao lsddetalightweightdetectorforsmallshiptargetsinsarimages |