A Dual-Polarization Information-Guided Network for SAR Ship Classification
Synthetic aperture radar (SAR) is an advanced active microwave sensor widely used in marine surveillance. As part of typical marine surveillance missions, ship classification in synthetic aperture radar (SAR) images is a significant task for the remote sensing community. However, fully utilizing pol...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/8/2138 |
| _version_ | 1827743737235636224 |
|---|---|
| author | Zikang Shao Tianwen Zhang Xiao Ke |
| author_facet | Zikang Shao Tianwen Zhang Xiao Ke |
| author_sort | Zikang Shao |
| collection | DOAJ |
| description | Synthetic aperture radar (SAR) is an advanced active microwave sensor widely used in marine surveillance. As part of typical marine surveillance missions, ship classification in synthetic aperture radar (SAR) images is a significant task for the remote sensing community. However, fully utilizing polarization information to enhance SAR ship classification remains an unresolved issue. Thus, we proposed a dual-polarization information-guided network (DPIG-Net) to solve it. DPIG-Net utilizes available dual-polarization information from the Sentinel-1 SAR satellite to adaptively guide feature extraction and feature fusion. We first designed a novel polarization channel cross-attention framework (PCCAF) to model the correlations of different polarization information for feature extraction. Then, we established a novel dilated residual dense learning framework (DRDLF) to refine the polarization characteristics for feature fusion. The results on the open OpenSARShip dataset indicated DPIG-Net’s state-of-the-art classification accuracy compared with eleven other competitive models, which showed the potential of DPIG-Net to promote effective and sufficient utilization of SAR polarization data in the future. |
| first_indexed | 2024-03-11T04:33:43Z |
| format | Article |
| id | doaj.art-1f04ccb3b9f043ce8644e60e6b83f7b1 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T04:33:43Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-1f04ccb3b9f043ce8644e60e6b83f7b12023-11-17T21:12:35ZengMDPI AGRemote Sensing2072-42922023-04-01158213810.3390/rs15082138A Dual-Polarization Information-Guided Network for SAR Ship ClassificationZikang Shao0Tianwen Zhang1Xiao Ke2School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSynthetic aperture radar (SAR) is an advanced active microwave sensor widely used in marine surveillance. As part of typical marine surveillance missions, ship classification in synthetic aperture radar (SAR) images is a significant task for the remote sensing community. However, fully utilizing polarization information to enhance SAR ship classification remains an unresolved issue. Thus, we proposed a dual-polarization information-guided network (DPIG-Net) to solve it. DPIG-Net utilizes available dual-polarization information from the Sentinel-1 SAR satellite to adaptively guide feature extraction and feature fusion. We first designed a novel polarization channel cross-attention framework (PCCAF) to model the correlations of different polarization information for feature extraction. Then, we established a novel dilated residual dense learning framework (DRDLF) to refine the polarization characteristics for feature fusion. The results on the open OpenSARShip dataset indicated DPIG-Net’s state-of-the-art classification accuracy compared with eleven other competitive models, which showed the potential of DPIG-Net to promote effective and sufficient utilization of SAR polarization data in the future.https://www.mdpi.com/2072-4292/15/8/2138synthetic aperture radarship classificationpolarization-guided |
| spellingShingle | Zikang Shao Tianwen Zhang Xiao Ke A Dual-Polarization Information-Guided Network for SAR Ship Classification Remote Sensing synthetic aperture radar ship classification polarization-guided |
| title | A Dual-Polarization Information-Guided Network for SAR Ship Classification |
| title_full | A Dual-Polarization Information-Guided Network for SAR Ship Classification |
| title_fullStr | A Dual-Polarization Information-Guided Network for SAR Ship Classification |
| title_full_unstemmed | A Dual-Polarization Information-Guided Network for SAR Ship Classification |
| title_short | A Dual-Polarization Information-Guided Network for SAR Ship Classification |
| title_sort | dual polarization information guided network for sar ship classification |
| topic | synthetic aperture radar ship classification polarization-guided |
| url | https://www.mdpi.com/2072-4292/15/8/2138 |
| work_keys_str_mv | AT zikangshao adualpolarizationinformationguidednetworkforsarshipclassification AT tianwenzhang adualpolarizationinformationguidednetworkforsarshipclassification AT xiaoke adualpolarizationinformationguidednetworkforsarshipclassification AT zikangshao dualpolarizationinformationguidednetworkforsarshipclassification AT tianwenzhang dualpolarizationinformationguidednetworkforsarshipclassification AT xiaoke dualpolarizationinformationguidednetworkforsarshipclassification |