SAR Small Ship Detection Based on Enhanced YOLO Network
Ships are important targets for marine surveillance in both military and civilian domains. Since the rise of deep learning, ship detection in synthetic aperture radar (SAR) images has achieved significant progress. However, the variability in ship size and resolution, especially the widespread prese...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/5/839 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850030244878090240 |
|---|---|
| author | Tianyue Guan Sheng Chang Chunle Wang Xiaoxue Jia |
| author_facet | Tianyue Guan Sheng Chang Chunle Wang Xiaoxue Jia |
| author_sort | Tianyue Guan |
| collection | DOAJ |
| description | Ships are important targets for marine surveillance in both military and civilian domains. Since the rise of deep learning, ship detection in synthetic aperture radar (SAR) images has achieved significant progress. However, the variability in ship size and resolution, especially the widespread presence of numerous small-sized ships, continues to pose challenges for effective ship detection in SAR images. To address the challenges posed by small ship targets, we propose an enhanced YOLO network to improve the detection accuracy of small targets. Firstly, we propose a Shuffle Re-parameterization (SR) module as a replacement for the C2f module in the original YOLOv8 network. The SR module employs re-parameterized convolution along with channel shuffle operations to improve feature extraction capabilities. Secondly, we employ the space-to-depth (SPD) module to perform down-sampling operations within the backbone network, thereby reducing the information loss associated with pooling operations. Thirdly, we incorporate a Hybrid Attention (HA) module into the neck network to enhance the feature representation of small ship targets while mitigating the interference caused by surrounding sea clutter and speckle noise. Finally, we add the shape-NWD loss to the regression loss, which emphasizes the shape and scale of the bounding box and mitigates the sensitivity of Intersection over Union (IoU) to positional deviations in small ship targets. Extensive experiments were carried out on three publicly available datasets—namely, LS-SSDD, HRSID, and iVision-MRSSD—to demonstrate the effectiveness and reliability of the proposed method. In the small ship dataset LS-SSDD, the proposed method exhibits a notable improvement in average precision at an IoU threshold of 0.5 (AP50), surpassing the baseline network by over 4%, and achieving an AP50 of 77.2%. In the HRSID and iVision-MRSSD datasets, AP50 reaches 91% and 95%, respectively. Additionally, the average precision for small targets (AP) exhibits an increase of approximately 2% across both datasets. Furthermore, the proposed method demonstrates outstanding performance in comparison experiments across all three datasets, outperforming existing state-of-the-art target detection methods. The experimental results offer compelling evidence supporting the superior performance and practical applicability of the proposed method in SAR small ship detection. |
| format | Article |
| id | doaj-art-29e4750d8a5b4b6bac1ee63b5e1cdd36 |
| institution | DOAJ |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-29e4750d8a5b4b6bac1ee63b5e1cdd362025-08-20T02:59:15ZengMDPI AGRemote Sensing2072-42922025-02-0117583910.3390/rs17050839SAR Small Ship Detection Based on Enhanced YOLO NetworkTianyue Guan0Sheng Chang1Chunle Wang2Xiaoxue Jia3Space Microwave Remote Sensing System Department, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, ChinaSpace Microwave Remote Sensing System Department, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, ChinaSpace Microwave Remote Sensing System Department, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, ChinaSpace Microwave Remote Sensing System Department, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, ChinaShips are important targets for marine surveillance in both military and civilian domains. Since the rise of deep learning, ship detection in synthetic aperture radar (SAR) images has achieved significant progress. However, the variability in ship size and resolution, especially the widespread presence of numerous small-sized ships, continues to pose challenges for effective ship detection in SAR images. To address the challenges posed by small ship targets, we propose an enhanced YOLO network to improve the detection accuracy of small targets. Firstly, we propose a Shuffle Re-parameterization (SR) module as a replacement for the C2f module in the original YOLOv8 network. The SR module employs re-parameterized convolution along with channel shuffle operations to improve feature extraction capabilities. Secondly, we employ the space-to-depth (SPD) module to perform down-sampling operations within the backbone network, thereby reducing the information loss associated with pooling operations. Thirdly, we incorporate a Hybrid Attention (HA) module into the neck network to enhance the feature representation of small ship targets while mitigating the interference caused by surrounding sea clutter and speckle noise. Finally, we add the shape-NWD loss to the regression loss, which emphasizes the shape and scale of the bounding box and mitigates the sensitivity of Intersection over Union (IoU) to positional deviations in small ship targets. Extensive experiments were carried out on three publicly available datasets—namely, LS-SSDD, HRSID, and iVision-MRSSD—to demonstrate the effectiveness and reliability of the proposed method. In the small ship dataset LS-SSDD, the proposed method exhibits a notable improvement in average precision at an IoU threshold of 0.5 (AP50), surpassing the baseline network by over 4%, and achieving an AP50 of 77.2%. In the HRSID and iVision-MRSSD datasets, AP50 reaches 91% and 95%, respectively. Additionally, the average precision for small targets (AP) exhibits an increase of approximately 2% across both datasets. Furthermore, the proposed method demonstrates outstanding performance in comparison experiments across all three datasets, outperforming existing state-of-the-art target detection methods. The experimental results offer compelling evidence supporting the superior performance and practical applicability of the proposed method in SAR small ship detection.https://www.mdpi.com/2072-4292/17/5/839synthetic aperture radar (SAR)small ship detectionyou only look once (YOLO)re-parameterized convolution |
| spellingShingle | Tianyue Guan Sheng Chang Chunle Wang Xiaoxue Jia SAR Small Ship Detection Based on Enhanced YOLO Network Remote Sensing synthetic aperture radar (SAR) small ship detection you only look once (YOLO) re-parameterized convolution |
| title | SAR Small Ship Detection Based on Enhanced YOLO Network |
| title_full | SAR Small Ship Detection Based on Enhanced YOLO Network |
| title_fullStr | SAR Small Ship Detection Based on Enhanced YOLO Network |
| title_full_unstemmed | SAR Small Ship Detection Based on Enhanced YOLO Network |
| title_short | SAR Small Ship Detection Based on Enhanced YOLO Network |
| title_sort | sar small ship detection based on enhanced yolo network |
| topic | synthetic aperture radar (SAR) small ship detection you only look once (YOLO) re-parameterized convolution |
| url | https://www.mdpi.com/2072-4292/17/5/839 |
| work_keys_str_mv | AT tianyueguan sarsmallshipdetectionbasedonenhancedyolonetwork AT shengchang sarsmallshipdetectionbasedonenhancedyolonetwork AT chunlewang sarsmallshipdetectionbasedonenhancedyolonetwork AT xiaoxuejia sarsmallshipdetectionbasedonenhancedyolonetwork |