An SAR Ship Object Detection Algorithm Based on Feature Information Efficient Representation Network
In the synthetic aperture radar (SAR) ship image, the target size is small and dense, the background is complex and changeable, the ship target is difficult to distinguish from the surrounding background, and there are many ship-like targets in the image. This makes it difficult for deep-learning-ba...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/14/3489 |
| _version_ | 1827618646121250816 |
|---|---|
| author | Jimin Yu Tao Wu Shangbo Zhou Huilan Pan Xin Zhang Wei Zhang |
| author_facet | Jimin Yu Tao Wu Shangbo Zhou Huilan Pan Xin Zhang Wei Zhang |
| author_sort | Jimin Yu |
| collection | DOAJ |
| description | In the synthetic aperture radar (SAR) ship image, the target size is small and dense, the background is complex and changeable, the ship target is difficult to distinguish from the surrounding background, and there are many ship-like targets in the image. This makes it difficult for deep-learning-based target detection algorithms to obtain effective feature information, resulting in missed and false detection. The effective expression of the feature information of the target to be detected is the key to the target detection algorithm. How to improve the clear expression of image feature information in the network has always been a difficult point. Aiming at the above problems, this paper proposes a new target detection algorithm, the feature information efficient representation network (FIERNet). The algorithm can extract better feature details, enhance network feature fusion and information expression, and improve model detection capabilities. First, the convolution transformer feature extraction (CTFE) module is proposed, and a convolution transformer feature extraction network (CTFENet) is built with this module as a feature extraction block. The network enables the model to obtain more accurate and comprehensive feature information, weakens the interference of invalid information, and improves the overall performance of the network. Second, a new effective feature information fusion (EFIF) module is proposed to enhance the transfer and fusion of the main information of feature maps. Finally, a new frame-decoding formula is proposed to further improve the coincidence between the predicted frame and the target frame and obtain more accurate picture information. Experiments show that the method achieves 94.14% and 92.01% mean precision (mAP) on SSDD and SAR-ship datasets, and it works well on large-scale SAR ship images. In addition, FIERNet greatly reduces the occurrence of missed detection and false detection in SAR ship detection. Compared to other state-of-the-art object detection algorithms, FIERNet outperforms them on various performance metrics on SAR images. |
| first_indexed | 2024-03-09T10:12:32Z |
| format | Article |
| id | doaj.art-7129b10d4343492d8b017d17e5e7edc3 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T10:12:32Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-7129b10d4343492d8b017d17e5e7edc32023-12-01T22:39:20ZengMDPI AGRemote Sensing2072-42922022-07-011414348910.3390/rs14143489An SAR Ship Object Detection Algorithm Based on Feature Information Efficient Representation NetworkJimin Yu0Tao Wu1Shangbo Zhou2Huilan Pan3Xin Zhang4Wei Zhang5College of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaCollege of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaCollege of Computer Science, Chongqing University, Chongqing 400044, ChinaSchool of Science, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaCollege of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaCollege of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaIn the synthetic aperture radar (SAR) ship image, the target size is small and dense, the background is complex and changeable, the ship target is difficult to distinguish from the surrounding background, and there are many ship-like targets in the image. This makes it difficult for deep-learning-based target detection algorithms to obtain effective feature information, resulting in missed and false detection. The effective expression of the feature information of the target to be detected is the key to the target detection algorithm. How to improve the clear expression of image feature information in the network has always been a difficult point. Aiming at the above problems, this paper proposes a new target detection algorithm, the feature information efficient representation network (FIERNet). The algorithm can extract better feature details, enhance network feature fusion and information expression, and improve model detection capabilities. First, the convolution transformer feature extraction (CTFE) module is proposed, and a convolution transformer feature extraction network (CTFENet) is built with this module as a feature extraction block. The network enables the model to obtain more accurate and comprehensive feature information, weakens the interference of invalid information, and improves the overall performance of the network. Second, a new effective feature information fusion (EFIF) module is proposed to enhance the transfer and fusion of the main information of feature maps. Finally, a new frame-decoding formula is proposed to further improve the coincidence between the predicted frame and the target frame and obtain more accurate picture information. Experiments show that the method achieves 94.14% and 92.01% mean precision (mAP) on SSDD and SAR-ship datasets, and it works well on large-scale SAR ship images. In addition, FIERNet greatly reduces the occurrence of missed detection and false detection in SAR ship detection. Compared to other state-of-the-art object detection algorithms, FIERNet outperforms them on various performance metrics on SAR images.https://www.mdpi.com/2072-4292/14/14/3489FIERNetCTFECTFENetEFIF modulebounding box regression decodingSAR ship detection |
| spellingShingle | Jimin Yu Tao Wu Shangbo Zhou Huilan Pan Xin Zhang Wei Zhang An SAR Ship Object Detection Algorithm Based on Feature Information Efficient Representation Network Remote Sensing FIERNet CTFE CTFENet EFIF module bounding box regression decoding SAR ship detection |
| title | An SAR Ship Object Detection Algorithm Based on Feature Information Efficient Representation Network |
| title_full | An SAR Ship Object Detection Algorithm Based on Feature Information Efficient Representation Network |
| title_fullStr | An SAR Ship Object Detection Algorithm Based on Feature Information Efficient Representation Network |
| title_full_unstemmed | An SAR Ship Object Detection Algorithm Based on Feature Information Efficient Representation Network |
| title_short | An SAR Ship Object Detection Algorithm Based on Feature Information Efficient Representation Network |
| title_sort | sar ship object detection algorithm based on feature information efficient representation network |
| topic | FIERNet CTFE CTFENet EFIF module bounding box regression decoding SAR ship detection |
| url | https://www.mdpi.com/2072-4292/14/14/3489 |
| work_keys_str_mv | AT jiminyu ansarshipobjectdetectionalgorithmbasedonfeatureinformationefficientrepresentationnetwork AT taowu ansarshipobjectdetectionalgorithmbasedonfeatureinformationefficientrepresentationnetwork AT shangbozhou ansarshipobjectdetectionalgorithmbasedonfeatureinformationefficientrepresentationnetwork AT huilanpan ansarshipobjectdetectionalgorithmbasedonfeatureinformationefficientrepresentationnetwork AT xinzhang ansarshipobjectdetectionalgorithmbasedonfeatureinformationefficientrepresentationnetwork AT weizhang ansarshipobjectdetectionalgorithmbasedonfeatureinformationefficientrepresentationnetwork AT jiminyu sarshipobjectdetectionalgorithmbasedonfeatureinformationefficientrepresentationnetwork AT taowu sarshipobjectdetectionalgorithmbasedonfeatureinformationefficientrepresentationnetwork AT shangbozhou sarshipobjectdetectionalgorithmbasedonfeatureinformationefficientrepresentationnetwork AT huilanpan sarshipobjectdetectionalgorithmbasedonfeatureinformationefficientrepresentationnetwork AT xinzhang sarshipobjectdetectionalgorithmbasedonfeatureinformationefficientrepresentationnetwork AT weizhang sarshipobjectdetectionalgorithmbasedonfeatureinformationefficientrepresentationnetwork |