A Lightweight Network for Ship Detection in SAR Images Based on Edge Feature Aware and Fusion
Recently, with the increasing adoption of synthetic aperture radar (SAR) ship detection methods on mobile platforms, the lightweighting of detection methods has become a research focus. Despite certain achievements, there are still several limitations: 1) Existing studies have mainly focused on redu...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10818772/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590379164106752 |
|---|---|
| author | Yuming Li Jin Liu Xingye Li Xiliang Zhang Zhongdai Wu Bing Han |
| author_facet | Yuming Li Jin Liu Xingye Li Xiliang Zhang Zhongdai Wu Bing Han |
| author_sort | Yuming Li |
| collection | DOAJ |
| description | Recently, with the increasing adoption of synthetic aperture radar (SAR) ship detection methods on mobile platforms, the lightweighting of detection methods has become a research focus. Despite certain achievements, there are still several limitations: 1) Existing studies have mainly focused on reducing model complexity through shallow network structures. However, this approach frequently results in performance degradation, as they neglected a thorough investigation into achieving a better balance point between inference speed and detection accuracy. 2) Under the lightweight network structure, the rich edge features contained in SAR images, which are crucial for distinguishing ship targets from complex backgrounds, are often underutilized. To address these issues, we propose a novel lightweight detection method based on edge feature aware and fusion. Specifically, to effectively extract edge feature, we introduce an Edge Feature-Aware (EFA) network that incorporates a multiscale channel attention module. Furthermore, a lightweight feature fusion network, Filter-Pruned Bi-directional Feature Pyramid Network (FP-BiFPN), is carefully designed, which can not only suppresses background information, but also accentuates ship targets. Finally, we propose a selective quantization algorithm based on a bit-width selection mechanism to reduce model memory usage without compromising performance. To validate the superiority of our proposed method, we conduct extensive experiments on multiple public datasets, achieving average accuracy scores of 94.2%, 97.6%, and 97.7% on the HRSID, SAR-Ship-Dataset, and SSDD, respectively, with a model parameter size of only 3.36 M, and the fastest processing time for a single frame is 7.2 ms. |
| format | Article |
| id | doaj-art-1e5e887f625945f2b7e18f2a3ce0a733 |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-1e5e887f625945f2b7e18f2a3ce0a7332025-01-24T00:01:00ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01183782379610.1109/JSTARS.2024.352440210818772A Lightweight Network for Ship Detection in SAR Images Based on Edge Feature Aware and FusionYuming Li0https://orcid.org/0009-0007-0770-4237Jin Liu1https://orcid.org/0000-0001-7249-698XXingye Li2https://orcid.org/0000-0002-5727-8877Xiliang Zhang3https://orcid.org/0000-0001-8529-1350Zhongdai Wu4https://orcid.org/0009-0001-3388-9446Bing Han5https://orcid.org/0000-0002-3020-3015College of Information Engineering, Shanghai Maritime University, Shanghai, ChinaCollege of Information Engineering, Shanghai Maritime University, Shanghai, ChinaCollege of Information Engineering, Shanghai Maritime University, Shanghai, ChinaCollege of Information Engineering, Shanghai Maritime University, Shanghai, ChinaShanghai Ship and Shipping Research Institute Company Ltd., Shanghai, ChinaShanghai Ship and Shipping Research Institute Company Ltd., Shanghai, ChinaRecently, with the increasing adoption of synthetic aperture radar (SAR) ship detection methods on mobile platforms, the lightweighting of detection methods has become a research focus. Despite certain achievements, there are still several limitations: 1) Existing studies have mainly focused on reducing model complexity through shallow network structures. However, this approach frequently results in performance degradation, as they neglected a thorough investigation into achieving a better balance point between inference speed and detection accuracy. 2) Under the lightweight network structure, the rich edge features contained in SAR images, which are crucial for distinguishing ship targets from complex backgrounds, are often underutilized. To address these issues, we propose a novel lightweight detection method based on edge feature aware and fusion. Specifically, to effectively extract edge feature, we introduce an Edge Feature-Aware (EFA) network that incorporates a multiscale channel attention module. Furthermore, a lightweight feature fusion network, Filter-Pruned Bi-directional Feature Pyramid Network (FP-BiFPN), is carefully designed, which can not only suppresses background information, but also accentuates ship targets. Finally, we propose a selective quantization algorithm based on a bit-width selection mechanism to reduce model memory usage without compromising performance. To validate the superiority of our proposed method, we conduct extensive experiments on multiple public datasets, achieving average accuracy scores of 94.2%, 97.6%, and 97.7% on the HRSID, SAR-Ship-Dataset, and SSDD, respectively, with a model parameter size of only 3.36 M, and the fastest processing time for a single frame is 7.2 ms.https://ieeexplore.ieee.org/document/10818772/Deep learninglightweight networkship detectionsynthetic aperture radar (SAR) |
| spellingShingle | Yuming Li Jin Liu Xingye Li Xiliang Zhang Zhongdai Wu Bing Han A Lightweight Network for Ship Detection in SAR Images Based on Edge Feature Aware and Fusion IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Deep learning lightweight network ship detection synthetic aperture radar (SAR) |
| title | A Lightweight Network for Ship Detection in SAR Images Based on Edge Feature Aware and Fusion |
| title_full | A Lightweight Network for Ship Detection in SAR Images Based on Edge Feature Aware and Fusion |
| title_fullStr | A Lightweight Network for Ship Detection in SAR Images Based on Edge Feature Aware and Fusion |
| title_full_unstemmed | A Lightweight Network for Ship Detection in SAR Images Based on Edge Feature Aware and Fusion |
| title_short | A Lightweight Network for Ship Detection in SAR Images Based on Edge Feature Aware and Fusion |
| title_sort | lightweight network for ship detection in sar images based on edge feature aware and fusion |
| topic | Deep learning lightweight network ship detection synthetic aperture radar (SAR) |
| url | https://ieeexplore.ieee.org/document/10818772/ |
| work_keys_str_mv | AT yumingli alightweightnetworkforshipdetectioninsarimagesbasedonedgefeatureawareandfusion AT jinliu alightweightnetworkforshipdetectioninsarimagesbasedonedgefeatureawareandfusion AT xingyeli alightweightnetworkforshipdetectioninsarimagesbasedonedgefeatureawareandfusion AT xiliangzhang alightweightnetworkforshipdetectioninsarimagesbasedonedgefeatureawareandfusion AT zhongdaiwu alightweightnetworkforshipdetectioninsarimagesbasedonedgefeatureawareandfusion AT binghan alightweightnetworkforshipdetectioninsarimagesbasedonedgefeatureawareandfusion AT yumingli lightweightnetworkforshipdetectioninsarimagesbasedonedgefeatureawareandfusion AT jinliu lightweightnetworkforshipdetectioninsarimagesbasedonedgefeatureawareandfusion AT xingyeli lightweightnetworkforshipdetectioninsarimagesbasedonedgefeatureawareandfusion AT xiliangzhang lightweightnetworkforshipdetectioninsarimagesbasedonedgefeatureawareandfusion AT zhongdaiwu lightweightnetworkforshipdetectioninsarimagesbasedonedgefeatureawareandfusion AT binghan lightweightnetworkforshipdetectioninsarimagesbasedonedgefeatureawareandfusion |