A Three-Branch Pansharpening Network Based on Spatial and Frequency Domain Interaction
Pansharpening technology plays a crucial role in remote sensing image processing by integrating low-resolution multispectral (LRMS) images and high-resolution panchromatic (PAN) images to generate high-resolution multispectral (HRMS) images. This process addresses the limitations of satellite sensor...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/1/13 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549017570344960 |
|---|---|
| author | Xincan Wen Hongbing Ma Liangliang Li |
| author_facet | Xincan Wen Hongbing Ma Liangliang Li |
| author_sort | Xincan Wen |
| collection | DOAJ |
| description | Pansharpening technology plays a crucial role in remote sensing image processing by integrating low-resolution multispectral (LRMS) images and high-resolution panchromatic (PAN) images to generate high-resolution multispectral (HRMS) images. This process addresses the limitations of satellite sensors, which cannot directly capture HRMS images. Despite significant developments achieved by deep learning-based pansharpening methods over traditional approaches, most existing techniques either fail to account for the modal differences between LRMS and PAN images, relying on direct concatenation, or use similar network structures to extract spectral and spatial information. Additionally, many methods neglect the extraction of common features between LRMS and PAN images and lack network architectures specifically designed to extract spectral features. To address these limitations, this study proposed a novel three-branch pansharpening network that leverages both spatial and frequency domain interactions, resulting in improved spectral and spatial fidelity in the fusion outputs. The proposed method was validated on three datasets, including IKONOS, WorldView-3 (WV3), and WorldView-4 (WV4). The results demonstrate that the proposed method surpasses several leading techniques, achieving superior performance in both visual quality and quantitative metrics. |
| format | Article |
| id | doaj-art-bbb821681d94489fbece66305a929af5 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-bbb821681d94489fbece66305a929af52025-01-10T13:19:57ZengMDPI AGRemote Sensing2072-42922024-12-011711310.3390/rs17010013A Three-Branch Pansharpening Network Based on Spatial and Frequency Domain InteractionXincan Wen0Hongbing Ma1Liangliang Li2School of Computer Science and Technology, Xinjiang University, Urumqi 830046, ChinaSchool of Computer Science and Technology, Xinjiang University, Urumqi 830046, ChinaSchool of Information and Electronics, Beijing Institute of Technology, Beijing 100081, ChinaPansharpening technology plays a crucial role in remote sensing image processing by integrating low-resolution multispectral (LRMS) images and high-resolution panchromatic (PAN) images to generate high-resolution multispectral (HRMS) images. This process addresses the limitations of satellite sensors, which cannot directly capture HRMS images. Despite significant developments achieved by deep learning-based pansharpening methods over traditional approaches, most existing techniques either fail to account for the modal differences between LRMS and PAN images, relying on direct concatenation, or use similar network structures to extract spectral and spatial information. Additionally, many methods neglect the extraction of common features between LRMS and PAN images and lack network architectures specifically designed to extract spectral features. To address these limitations, this study proposed a novel three-branch pansharpening network that leverages both spatial and frequency domain interactions, resulting in improved spectral and spatial fidelity in the fusion outputs. The proposed method was validated on three datasets, including IKONOS, WorldView-3 (WV3), and WorldView-4 (WV4). The results demonstrate that the proposed method surpasses several leading techniques, achieving superior performance in both visual quality and quantitative metrics.https://www.mdpi.com/2072-4292/17/1/13pansharpeningdeep learningthree branchinteraction |
| spellingShingle | Xincan Wen Hongbing Ma Liangliang Li A Three-Branch Pansharpening Network Based on Spatial and Frequency Domain Interaction Remote Sensing pansharpening deep learning three branch interaction |
| title | A Three-Branch Pansharpening Network Based on Spatial and Frequency Domain Interaction |
| title_full | A Three-Branch Pansharpening Network Based on Spatial and Frequency Domain Interaction |
| title_fullStr | A Three-Branch Pansharpening Network Based on Spatial and Frequency Domain Interaction |
| title_full_unstemmed | A Three-Branch Pansharpening Network Based on Spatial and Frequency Domain Interaction |
| title_short | A Three-Branch Pansharpening Network Based on Spatial and Frequency Domain Interaction |
| title_sort | three branch pansharpening network based on spatial and frequency domain interaction |
| topic | pansharpening deep learning three branch interaction |
| url | https://www.mdpi.com/2072-4292/17/1/13 |
| work_keys_str_mv | AT xincanwen athreebranchpansharpeningnetworkbasedonspatialandfrequencydomaininteraction AT hongbingma athreebranchpansharpeningnetworkbasedonspatialandfrequencydomaininteraction AT liangliangli athreebranchpansharpeningnetworkbasedonspatialandfrequencydomaininteraction AT xincanwen threebranchpansharpeningnetworkbasedonspatialandfrequencydomaininteraction AT hongbingma threebranchpansharpeningnetworkbasedonspatialandfrequencydomaininteraction AT liangliangli threebranchpansharpeningnetworkbasedonspatialandfrequencydomaininteraction |