A New Deep Neural Network Based on SwinT-FRM-ShipNet for SAR Ship Detection in Complex Near-Shore and Offshore Environments
The advent of deep learning has significantly propelled the utilization of neural networks for Synthetic Aperture Radar (SAR) ship detection in recent years. However, there are two main obstacles in SAR detection. Challenge 1: The multiscale nature of SAR ships. Challenge 2: The influence of intrica...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/24/5780 |
| _version_ | 1797379466462232576 |
|---|---|
| author | Zhuhao Lu Pengfei Wang Yajun Li Baogang Ding |
| author_facet | Zhuhao Lu Pengfei Wang Yajun Li Baogang Ding |
| author_sort | Zhuhao Lu |
| collection | DOAJ |
| description | The advent of deep learning has significantly propelled the utilization of neural networks for Synthetic Aperture Radar (SAR) ship detection in recent years. However, there are two main obstacles in SAR detection. Challenge 1: The multiscale nature of SAR ships. Challenge 2: The influence of intricate near-shore environments and the interference of clutter noise in offshore areas, especially affecting small-ship detection. Existing neural network-based approaches attempt to tackle these challenges, yet they often fall short in effectively addressing small-ship detection across multiple scales and complex backgrounds simultaneously. To overcome these challenges, we propose a novel network called SwinT-FRM-ShipNet. Our method introduces an integrated feature extractor, Swin-T-YOLOv5l, which combines Swin Transformer and YOLOv5l. The extractor is designed to highlight the differences between the complex background and the target by encoding both local and global information. Additionally, a feature pyramid IEFR-FPN, consisting of the Information Enhancement Module (IEM) and the Feature Refinement Module (FRM), is proposed to enrich the flow of spatial contextual information, fuse multiresolution features, and refine representations of small and multiscale ships. Furthermore, we introduce recursive gated convolutional prediction heads (GCPH) to explore the potential of high-order spatial interactions and add a larger-sized prediction head to focus on small ships. Experimental results demonstrate the superior performance of our method compared to mainstream approaches on the SSDD and SAR-Ship-Dataset. Our method achieves an F1 score, mAP<sub>0.5</sub>, and mAP<sub>0.5:0.95</sub> of 96.5% (+0.9), 98.2% (+1.0%), and 75.4% (+3.3%), respectively, surpassing the most competitive algorithms. |
| first_indexed | 2024-03-08T20:23:38Z |
| format | Article |
| id | doaj.art-02232598965a4abc96903da1a5661774 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-08T20:23:38Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-02232598965a4abc96903da1a56617742023-12-22T14:39:19ZengMDPI AGRemote Sensing2072-42922023-12-011524578010.3390/rs15245780A New Deep Neural Network Based on SwinT-FRM-ShipNet for SAR Ship Detection in Complex Near-Shore and Offshore EnvironmentsZhuhao Lu0Pengfei Wang1Yajun Li2Baogang Ding3The Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai 200241, ChinaThe Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai 200241, ChinaThe Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai 200241, ChinaThe Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai 200241, ChinaThe advent of deep learning has significantly propelled the utilization of neural networks for Synthetic Aperture Radar (SAR) ship detection in recent years. However, there are two main obstacles in SAR detection. Challenge 1: The multiscale nature of SAR ships. Challenge 2: The influence of intricate near-shore environments and the interference of clutter noise in offshore areas, especially affecting small-ship detection. Existing neural network-based approaches attempt to tackle these challenges, yet they often fall short in effectively addressing small-ship detection across multiple scales and complex backgrounds simultaneously. To overcome these challenges, we propose a novel network called SwinT-FRM-ShipNet. Our method introduces an integrated feature extractor, Swin-T-YOLOv5l, which combines Swin Transformer and YOLOv5l. The extractor is designed to highlight the differences between the complex background and the target by encoding both local and global information. Additionally, a feature pyramid IEFR-FPN, consisting of the Information Enhancement Module (IEM) and the Feature Refinement Module (FRM), is proposed to enrich the flow of spatial contextual information, fuse multiresolution features, and refine representations of small and multiscale ships. Furthermore, we introduce recursive gated convolutional prediction heads (GCPH) to explore the potential of high-order spatial interactions and add a larger-sized prediction head to focus on small ships. Experimental results demonstrate the superior performance of our method compared to mainstream approaches on the SSDD and SAR-Ship-Dataset. Our method achieves an F1 score, mAP<sub>0.5</sub>, and mAP<sub>0.5:0.95</sub> of 96.5% (+0.9), 98.2% (+1.0%), and 75.4% (+3.3%), respectively, surpassing the most competitive algorithms.https://www.mdpi.com/2072-4292/15/24/5780SARmultiscalecomplex backgroundsship detectiondeep learning |
| spellingShingle | Zhuhao Lu Pengfei Wang Yajun Li Baogang Ding A New Deep Neural Network Based on SwinT-FRM-ShipNet for SAR Ship Detection in Complex Near-Shore and Offshore Environments Remote Sensing SAR multiscale complex backgrounds ship detection deep learning |
| title | A New Deep Neural Network Based on SwinT-FRM-ShipNet for SAR Ship Detection in Complex Near-Shore and Offshore Environments |
| title_full | A New Deep Neural Network Based on SwinT-FRM-ShipNet for SAR Ship Detection in Complex Near-Shore and Offshore Environments |
| title_fullStr | A New Deep Neural Network Based on SwinT-FRM-ShipNet for SAR Ship Detection in Complex Near-Shore and Offshore Environments |
| title_full_unstemmed | A New Deep Neural Network Based on SwinT-FRM-ShipNet for SAR Ship Detection in Complex Near-Shore and Offshore Environments |
| title_short | A New Deep Neural Network Based on SwinT-FRM-ShipNet for SAR Ship Detection in Complex Near-Shore and Offshore Environments |
| title_sort | new deep neural network based on swint frm shipnet for sar ship detection in complex near shore and offshore environments |
| topic | SAR multiscale complex backgrounds ship detection deep learning |
| url | https://www.mdpi.com/2072-4292/15/24/5780 |
| work_keys_str_mv | AT zhuhaolu anewdeepneuralnetworkbasedonswintfrmshipnetforsarshipdetectionincomplexnearshoreandoffshoreenvironments AT pengfeiwang anewdeepneuralnetworkbasedonswintfrmshipnetforsarshipdetectionincomplexnearshoreandoffshoreenvironments AT yajunli anewdeepneuralnetworkbasedonswintfrmshipnetforsarshipdetectionincomplexnearshoreandoffshoreenvironments AT baogangding anewdeepneuralnetworkbasedonswintfrmshipnetforsarshipdetectionincomplexnearshoreandoffshoreenvironments AT zhuhaolu newdeepneuralnetworkbasedonswintfrmshipnetforsarshipdetectionincomplexnearshoreandoffshoreenvironments AT pengfeiwang newdeepneuralnetworkbasedonswintfrmshipnetforsarshipdetectionincomplexnearshoreandoffshoreenvironments AT yajunli newdeepneuralnetworkbasedonswintfrmshipnetforsarshipdetectionincomplexnearshoreandoffshoreenvironments AT baogangding newdeepneuralnetworkbasedonswintfrmshipnetforsarshipdetectionincomplexnearshoreandoffshoreenvironments |