Ship Recognition for SAR Scene Images under Imbalance Data
Synthetic aperture radar (SAR) ship recognition can obtain location and class information from SAR scene images, which is important in military and civilian fields, and has turned into a very important research focus recently. Limited by data conditions, the current research mainly includes two aspe...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/24/6294 |
| _version_ | 1797455438094008320 |
|---|---|
| author | Ronghui Zhan Zongyong Cui |
| author_facet | Ronghui Zhan Zongyong Cui |
| author_sort | Ronghui Zhan |
| collection | DOAJ |
| description | Synthetic aperture radar (SAR) ship recognition can obtain location and class information from SAR scene images, which is important in military and civilian fields, and has turned into a very important research focus recently. Limited by data conditions, the current research mainly includes two aspects: ship detection in SAR scene images and ship classification in SAR slice images. These two parts are not yet integrated, but it is necessary to integrate detection and classification in practical applications, although it will cause an imbalance of training samples for different classes. To solve these problems, this paper proposes a ship recognition method on the basis of a deep network to detect and classify ship targets in SAR scene images under imbalance data. First, RetinaNet is used as the backbone network of the method in this paper for the integration of ship detection and classification in SAR scene images. Then, taking into account the issue that there are high similarities among various SAR ship classes, the squeeze-and-excitation (SE) module is introduced for amplifying the difference features as well as reducing the similarity features. Finally, considering the problem of class imbalance in ship target recognition in SAR scene images, a loss function, the central focal loss (CEFL), based on depth feature aggregation is constructed to reduce the differences within classes. Based on the dataset from OpenSARShip and Sentinel-1, the results of the experiment suggest that the the proposed method is feasible and the accuracy of the proposed method is improved by 3.9 percentage points compared with the traditional RetinaNet. |
| first_indexed | 2024-03-09T15:54:24Z |
| format | Article |
| id | doaj.art-4ee1cdcf676947cb8dc526ff5fd6eb92 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T15:54:24Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-4ee1cdcf676947cb8dc526ff5fd6eb922023-11-24T17:47:19ZengMDPI AGRemote Sensing2072-42922022-12-011424629410.3390/rs14246294Ship Recognition for SAR Scene Images under Imbalance DataRonghui Zhan0Zongyong Cui1National Key Laboratory of Science and Technology on Automatic Target Recognition, National University of Defense Technology, Changsha 410073, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu 611731, ChinaSynthetic aperture radar (SAR) ship recognition can obtain location and class information from SAR scene images, which is important in military and civilian fields, and has turned into a very important research focus recently. Limited by data conditions, the current research mainly includes two aspects: ship detection in SAR scene images and ship classification in SAR slice images. These two parts are not yet integrated, but it is necessary to integrate detection and classification in practical applications, although it will cause an imbalance of training samples for different classes. To solve these problems, this paper proposes a ship recognition method on the basis of a deep network to detect and classify ship targets in SAR scene images under imbalance data. First, RetinaNet is used as the backbone network of the method in this paper for the integration of ship detection and classification in SAR scene images. Then, taking into account the issue that there are high similarities among various SAR ship classes, the squeeze-and-excitation (SE) module is introduced for amplifying the difference features as well as reducing the similarity features. Finally, considering the problem of class imbalance in ship target recognition in SAR scene images, a loss function, the central focal loss (CEFL), based on depth feature aggregation is constructed to reduce the differences within classes. Based on the dataset from OpenSARShip and Sentinel-1, the results of the experiment suggest that the the proposed method is feasible and the accuracy of the proposed method is improved by 3.9 percentage points compared with the traditional RetinaNet.https://www.mdpi.com/2072-4292/14/24/6294SAR scene imagesship recognitionsqueeze-and-excitation (SE) modulecentral focal loss (CEFL) |
| spellingShingle | Ronghui Zhan Zongyong Cui Ship Recognition for SAR Scene Images under Imbalance Data Remote Sensing SAR scene images ship recognition squeeze-and-excitation (SE) module central focal loss (CEFL) |
| title | Ship Recognition for SAR Scene Images under Imbalance Data |
| title_full | Ship Recognition for SAR Scene Images under Imbalance Data |
| title_fullStr | Ship Recognition for SAR Scene Images under Imbalance Data |
| title_full_unstemmed | Ship Recognition for SAR Scene Images under Imbalance Data |
| title_short | Ship Recognition for SAR Scene Images under Imbalance Data |
| title_sort | ship recognition for sar scene images under imbalance data |
| topic | SAR scene images ship recognition squeeze-and-excitation (SE) module central focal loss (CEFL) |
| url | https://www.mdpi.com/2072-4292/14/24/6294 |
| work_keys_str_mv | AT ronghuizhan shiprecognitionforsarsceneimagesunderimbalancedata AT zongyongcui shiprecognitionforsarsceneimagesunderimbalancedata |