YOLOv7oSAR: A Lightweight High-Precision Ship Detection Model for SAR Images Based on the YOLOv7 Algorithm
Researchers have explored various methods to fully exploit the all-weather characteristics of Synthetic aperture radar (SAR) images to achieve high-precision, real-time, computationally efficient, and easily deployable ship target detection models. These methods include Constant False Alarm Rate (CF...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/5/913 |
| _version_ | 1797263879196114944 |
|---|---|
| author | Yilin Liu Yong Ma Fu Chen Erping Shang Wutao Yao Shuyan Zhang Jin Yang |
| author_facet | Yilin Liu Yong Ma Fu Chen Erping Shang Wutao Yao Shuyan Zhang Jin Yang |
| author_sort | Yilin Liu |
| collection | DOAJ |
| description | Researchers have explored various methods to fully exploit the all-weather characteristics of Synthetic aperture radar (SAR) images to achieve high-precision, real-time, computationally efficient, and easily deployable ship target detection models. These methods include Constant False Alarm Rate (CFAR) algorithms and deep learning approaches such as RCNN, YOLO, and SSD, among others. While these methods outperform traditional algorithms in SAR ship detection, challenges still exist in handling the arbitrary ship distributions and small target features in SAR remote sensing images. Existing models are complex, with a large number of parameters, hindering effective deployment. This paper introduces a YOLOv7 oriented bounding box SAR ship detection model (YOLOv7oSAR). The model employs a rotation box detection mechanism, uses the KLD loss function to enhance accuracy, and introduces a Bi-former attention mechanism to improve small target detection. By redesigning the network’s width and depth and incorporating a lightweight P-ELAN structure, the model effectively reduces its size and computational requirements. The proposed model achieves high-precision detection results on the public RSDD dataset (94.8% offshore, 66.6% nearshore), and its generalization ability is validated on a custom dataset (94.2% overall detection accuracy). |
| first_indexed | 2024-04-25T00:20:01Z |
| format | Article |
| id | doaj.art-5d3d835c5a9b48aea356c1eb3123e7e6 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-04-25T00:20:01Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-5d3d835c5a9b48aea356c1eb3123e7e62024-03-12T16:54:25ZengMDPI AGRemote Sensing2072-42922024-03-0116591310.3390/rs16050913YOLOv7oSAR: A Lightweight High-Precision Ship Detection Model for SAR Images Based on the YOLOv7 AlgorithmYilin Liu0Yong Ma1Fu Chen2Erping Shang3Wutao Yao4Shuyan Zhang5Jin Yang6Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaResearchers have explored various methods to fully exploit the all-weather characteristics of Synthetic aperture radar (SAR) images to achieve high-precision, real-time, computationally efficient, and easily deployable ship target detection models. These methods include Constant False Alarm Rate (CFAR) algorithms and deep learning approaches such as RCNN, YOLO, and SSD, among others. While these methods outperform traditional algorithms in SAR ship detection, challenges still exist in handling the arbitrary ship distributions and small target features in SAR remote sensing images. Existing models are complex, with a large number of parameters, hindering effective deployment. This paper introduces a YOLOv7 oriented bounding box SAR ship detection model (YOLOv7oSAR). The model employs a rotation box detection mechanism, uses the KLD loss function to enhance accuracy, and introduces a Bi-former attention mechanism to improve small target detection. By redesigning the network’s width and depth and incorporating a lightweight P-ELAN structure, the model effectively reduces its size and computational requirements. The proposed model achieves high-precision detection results on the public RSDD dataset (94.8% offshore, 66.6% nearshore), and its generalization ability is validated on a custom dataset (94.2% overall detection accuracy).https://www.mdpi.com/2072-4292/16/5/913YOLO algorithmship detectionoriented bounding boxSynthetic aperture radar (SAR) images |
| spellingShingle | Yilin Liu Yong Ma Fu Chen Erping Shang Wutao Yao Shuyan Zhang Jin Yang YOLOv7oSAR: A Lightweight High-Precision Ship Detection Model for SAR Images Based on the YOLOv7 Algorithm Remote Sensing YOLO algorithm ship detection oriented bounding box Synthetic aperture radar (SAR) images |
| title | YOLOv7oSAR: A Lightweight High-Precision Ship Detection Model for SAR Images Based on the YOLOv7 Algorithm |
| title_full | YOLOv7oSAR: A Lightweight High-Precision Ship Detection Model for SAR Images Based on the YOLOv7 Algorithm |
| title_fullStr | YOLOv7oSAR: A Lightweight High-Precision Ship Detection Model for SAR Images Based on the YOLOv7 Algorithm |
| title_full_unstemmed | YOLOv7oSAR: A Lightweight High-Precision Ship Detection Model for SAR Images Based on the YOLOv7 Algorithm |
| title_short | YOLOv7oSAR: A Lightweight High-Precision Ship Detection Model for SAR Images Based on the YOLOv7 Algorithm |
| title_sort | yolov7osar a lightweight high precision ship detection model for sar images based on the yolov7 algorithm |
| topic | YOLO algorithm ship detection oriented bounding box Synthetic aperture radar (SAR) images |
| url | https://www.mdpi.com/2072-4292/16/5/913 |
| work_keys_str_mv | AT yilinliu yolov7osaralightweighthighprecisionshipdetectionmodelforsarimagesbasedontheyolov7algorithm AT yongma yolov7osaralightweighthighprecisionshipdetectionmodelforsarimagesbasedontheyolov7algorithm AT fuchen yolov7osaralightweighthighprecisionshipdetectionmodelforsarimagesbasedontheyolov7algorithm AT erpingshang yolov7osaralightweighthighprecisionshipdetectionmodelforsarimagesbasedontheyolov7algorithm AT wutaoyao yolov7osaralightweighthighprecisionshipdetectionmodelforsarimagesbasedontheyolov7algorithm AT shuyanzhang yolov7osaralightweighthighprecisionshipdetectionmodelforsarimagesbasedontheyolov7algorithm AT jinyang yolov7osaralightweighthighprecisionshipdetectionmodelforsarimagesbasedontheyolov7algorithm |