OSNet: An Edge Enhancement Network for a Joint Application of SAR and Optical Images
The combined use of synthetic aperture radar (SAR) and optical images for surface observation is gaining increasing attention. Optical images, with their distinct edge features, can accurately classify different objects, while SAR images reveal deeper internal variations. To address the challenge of...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/3/505 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850068238334951424 |
|---|---|
| author | Keyu Ma Kai Hu Junyu Chen Ming Jiang Yao Xu Min Xia Liguo Weng |
| author_facet | Keyu Ma Kai Hu Junyu Chen Ming Jiang Yao Xu Min Xia Liguo Weng |
| author_sort | Keyu Ma |
| collection | DOAJ |
| description | The combined use of synthetic aperture radar (SAR) and optical images for surface observation is gaining increasing attention. Optical images, with their distinct edge features, can accurately classify different objects, while SAR images reveal deeper internal variations. To address the challenge of differing feature distributions in multi-source images, we propose an edge enhancement network, OSNet (network for optical and SAR images), designed to jointly extract features from optical and SAR images and enhance edge feature representation. OSNet consists of three core modules: a dual-branch backbone, a synergistic attention integration module, and a global-guided local fusion module. These modules, respectively, handle modality-independent feature extraction, feature sharing, and global-local feature fusion. In the backbone module, we introduce a differentiable Lee filter and a Laplacian edge detection operator in the SAR branch to suppress noise and enhance edge features. Additionally, we designed a multi-source attention fusion module to facilitate cross-modal information exchange between the two branches. We validated OSNet’s performance on segmentation tasks (WHU-OPT-SAR) and regression tasks (SNOW-OPT-SAR). The results show that OSNet improved PA and MIoU by 2.31% and 2.58%, respectively, in the segmentation task, and reduced MAE and RMSE by 3.14% and 4.22%, respectively, in the regression task. |
| format | Article |
| id | doaj-art-5adbaa01bfa5445bbe3382a05aa9b764 |
| institution | DOAJ |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-5adbaa01bfa5445bbe3382a05aa9b7642025-08-20T02:48:07ZengMDPI AGRemote Sensing2072-42922025-01-0117350510.3390/rs17030505OSNet: An Edge Enhancement Network for a Joint Application of SAR and Optical ImagesKeyu Ma0Kai Hu1Junyu Chen2Ming Jiang3Yao Xu4Min Xia5Liguo Weng6School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaFaculty of Geosciences, Utrecht University, 3584 CS Utrecht, The NetherlandsDepartment of Computer Science, University of Reading, Whiteknights, Reading RG6 6DH, UKSchool of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaThe combined use of synthetic aperture radar (SAR) and optical images for surface observation is gaining increasing attention. Optical images, with their distinct edge features, can accurately classify different objects, while SAR images reveal deeper internal variations. To address the challenge of differing feature distributions in multi-source images, we propose an edge enhancement network, OSNet (network for optical and SAR images), designed to jointly extract features from optical and SAR images and enhance edge feature representation. OSNet consists of three core modules: a dual-branch backbone, a synergistic attention integration module, and a global-guided local fusion module. These modules, respectively, handle modality-independent feature extraction, feature sharing, and global-local feature fusion. In the backbone module, we introduce a differentiable Lee filter and a Laplacian edge detection operator in the SAR branch to suppress noise and enhance edge features. Additionally, we designed a multi-source attention fusion module to facilitate cross-modal information exchange between the two branches. We validated OSNet’s performance on segmentation tasks (WHU-OPT-SAR) and regression tasks (SNOW-OPT-SAR). The results show that OSNet improved PA and MIoU by 2.31% and 2.58%, respectively, in the segmentation task, and reduced MAE and RMSE by 3.14% and 4.22%, respectively, in the regression task.https://www.mdpi.com/2072-4292/17/3/505multimodal neural networksmulti-source fusionattention mechanism |
| spellingShingle | Keyu Ma Kai Hu Junyu Chen Ming Jiang Yao Xu Min Xia Liguo Weng OSNet: An Edge Enhancement Network for a Joint Application of SAR and Optical Images Remote Sensing multimodal neural networks multi-source fusion attention mechanism |
| title | OSNet: An Edge Enhancement Network for a Joint Application of SAR and Optical Images |
| title_full | OSNet: An Edge Enhancement Network for a Joint Application of SAR and Optical Images |
| title_fullStr | OSNet: An Edge Enhancement Network for a Joint Application of SAR and Optical Images |
| title_full_unstemmed | OSNet: An Edge Enhancement Network for a Joint Application of SAR and Optical Images |
| title_short | OSNet: An Edge Enhancement Network for a Joint Application of SAR and Optical Images |
| title_sort | osnet an edge enhancement network for a joint application of sar and optical images |
| topic | multimodal neural networks multi-source fusion attention mechanism |
| url | https://www.mdpi.com/2072-4292/17/3/505 |
| work_keys_str_mv | AT keyuma osnetanedgeenhancementnetworkforajointapplicationofsarandopticalimages AT kaihu osnetanedgeenhancementnetworkforajointapplicationofsarandopticalimages AT junyuchen osnetanedgeenhancementnetworkforajointapplicationofsarandopticalimages AT mingjiang osnetanedgeenhancementnetworkforajointapplicationofsarandopticalimages AT yaoxu osnetanedgeenhancementnetworkforajointapplicationofsarandopticalimages AT minxia osnetanedgeenhancementnetworkforajointapplicationofsarandopticalimages AT liguoweng osnetanedgeenhancementnetworkforajointapplicationofsarandopticalimages |