PCCN: Polarimetric Contexture Convolutional Network for PolSAR Image Super-Resolution
Polarimetric synthetic aperture radar (PolSAR) can acquire full-polarization information, which is the solid foundation for target scattering mechanism interpretation and utilization. Meanwhile, PolSAR image resolution is usually lower than the synthetic aperture radar (SAR) image, which may limit i...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10843849/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825207005663461376 |
|---|---|
| author | Lin-Yu Dai Ming-Dian Li Si-Wei Chen |
| author_facet | Lin-Yu Dai Ming-Dian Li Si-Wei Chen |
| author_sort | Lin-Yu Dai |
| collection | DOAJ |
| description | Polarimetric synthetic aperture radar (PolSAR) can acquire full-polarization information, which is the solid foundation for target scattering mechanism interpretation and utilization. Meanwhile, PolSAR image resolution is usually lower than the synthetic aperture radar (SAR) image, which may limit its potentials for target detection and recognition. Image super-resolution with the convolutional neural network is a promising solution to fulfill this issue. In order to make full use of both polarimetric and spatial information to further enhance super-resolution performance, this work proposes the polarimetric contexture convolutional network (PCCN) for PolSAR image super-resolution. The main contributions are threefold. First, a new PolSAR data representation of the polarimetric contexture matrix is established, which can fully represent the cube of polarimetric and spatial information into a coded matrix. Then, a dual-branch architecture of the polarimetric and spatial feature extraction block is designed to extract both polarimetric and spatial features separately. Finally, these intrinsic polarimetric and spatial features are effectively fused at both local and global levels for PolSAR image super-resolution. The proposed PCCN method is trained with one <italic>X</italic>-band polarimetric and interferometric synthetic aperture radar (PiSAR) data, while evaluated with the same scene but different PiSAR imaging direction and with different sensors data including the <italic>C</italic>-band Radarsat-2 and the <italic>X</italic>-band COSMO-SkyMed of various imaging scenes. Compared with state-of-the-art algorithms, experimental studies demonstrate and validate the effectiveness and superiority of the proposed method in both visualization examination and quantitative metrics. The proposed method can provide better super-resolution PolSAR images from both polarimetric and spatial viewpoints. |
| format | Article |
| id | doaj-art-25817ea684db4cea82687a2f70c7c142 |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-25817ea684db4cea82687a2f70c7c1422025-02-07T00:00:29ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01184664467910.1109/JSTARS.2025.353013610843849PCCN: Polarimetric Contexture Convolutional Network for PolSAR Image Super-ResolutionLin-Yu Dai0https://orcid.org/0009-0004-1665-6503Ming-Dian Li1https://orcid.org/0000-0002-4507-3233Si-Wei Chen2https://orcid.org/0000-0001-8713-7664College of Electronic Science and Technology, National University of Defense Technology, Changsha, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha, ChinaPolarimetric synthetic aperture radar (PolSAR) can acquire full-polarization information, which is the solid foundation for target scattering mechanism interpretation and utilization. Meanwhile, PolSAR image resolution is usually lower than the synthetic aperture radar (SAR) image, which may limit its potentials for target detection and recognition. Image super-resolution with the convolutional neural network is a promising solution to fulfill this issue. In order to make full use of both polarimetric and spatial information to further enhance super-resolution performance, this work proposes the polarimetric contexture convolutional network (PCCN) for PolSAR image super-resolution. The main contributions are threefold. First, a new PolSAR data representation of the polarimetric contexture matrix is established, which can fully represent the cube of polarimetric and spatial information into a coded matrix. Then, a dual-branch architecture of the polarimetric and spatial feature extraction block is designed to extract both polarimetric and spatial features separately. Finally, these intrinsic polarimetric and spatial features are effectively fused at both local and global levels for PolSAR image super-resolution. The proposed PCCN method is trained with one <italic>X</italic>-band polarimetric and interferometric synthetic aperture radar (PiSAR) data, while evaluated with the same scene but different PiSAR imaging direction and with different sensors data including the <italic>C</italic>-band Radarsat-2 and the <italic>X</italic>-band COSMO-SkyMed of various imaging scenes. Compared with state-of-the-art algorithms, experimental studies demonstrate and validate the effectiveness and superiority of the proposed method in both visualization examination and quantitative metrics. The proposed method can provide better super-resolution PolSAR images from both polarimetric and spatial viewpoints.https://ieeexplore.ieee.org/document/10843849/Convolutional neural network (CNN)polarimetric contexture matrixpolarimetric synthetic aperture radar (PolSAR)super-resolution |
| spellingShingle | Lin-Yu Dai Ming-Dian Li Si-Wei Chen PCCN: Polarimetric Contexture Convolutional Network for PolSAR Image Super-Resolution IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Convolutional neural network (CNN) polarimetric contexture matrix polarimetric synthetic aperture radar (PolSAR) super-resolution |
| title | PCCN: Polarimetric Contexture Convolutional Network for PolSAR Image Super-Resolution |
| title_full | PCCN: Polarimetric Contexture Convolutional Network for PolSAR Image Super-Resolution |
| title_fullStr | PCCN: Polarimetric Contexture Convolutional Network for PolSAR Image Super-Resolution |
| title_full_unstemmed | PCCN: Polarimetric Contexture Convolutional Network for PolSAR Image Super-Resolution |
| title_short | PCCN: Polarimetric Contexture Convolutional Network for PolSAR Image Super-Resolution |
| title_sort | pccn polarimetric contexture convolutional network for polsar image super resolution |
| topic | Convolutional neural network (CNN) polarimetric contexture matrix polarimetric synthetic aperture radar (PolSAR) super-resolution |
| url | https://ieeexplore.ieee.org/document/10843849/ |
| work_keys_str_mv | AT linyudai pccnpolarimetriccontextureconvolutionalnetworkforpolsarimagesuperresolution AT mingdianli pccnpolarimetriccontextureconvolutionalnetworkforpolsarimagesuperresolution AT siweichen pccnpolarimetriccontextureconvolutionalnetworkforpolsarimagesuperresolution |