ViT-ISRGAN: A High-Quality Super-Resolution Reconstruction Method for Multispectral Remote Sensing Images
The reflective characteristics of remote sensing image information depend on the scale of the observed area, with high-resolution images providing more detailed feature information. Currently, monitoring refined industries and extracting regional information necessitate higher-resolution remote sens...
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/10836746/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582364111306752 |
|---|---|
| author | Yifeng Yang Hengqian Zhao Xiadan Huangfu Zihan Li Pan Wang |
| author_facet | Yifeng Yang Hengqian Zhao Xiadan Huangfu Zihan Li Pan Wang |
| author_sort | Yifeng Yang |
| collection | DOAJ |
| description | The reflective characteristics of remote sensing image information depend on the scale of the observed area, with high-resolution images providing more detailed feature information. Currently, monitoring refined industries and extracting regional information necessitate higher-resolution remote sensing images. Super-resolution reconstruction of remote sensing multispectral images not only enhances the spatial resolution of these images but also preserves and improves the spectral information of multispectral data, thereby providing richer ground object information and more accurate environmental monitoring data. To improve the effectiveness of feature extraction in the generator network while maintaining model efficiency, this article proposes the vision transformer improved super-resolution generative adversarial network (ViT-ISRGAN) model. This model is an improvement upon the original SRGAN super-resolution image reconstruction method, incorporating lightweight network modules, channel attention modules, spatial-spectral residual attention, and the vision transformer structure. The ViT-ISRGAN model focuses on reconstructing four types of typical ground objects based on Sentinel-2 images: urban, water, farmland, and forest. Results indicate that the ViT-ISRGAN model excels in capturing texture details and color restoration, effectively extracting spectral and texture information from multispectral remote sensing images across various scenes. Compared to other super-resolution (SR) models, this approach demonstrates superior effectiveness and performance in the SR tasks of remote sensing multispectral images. |
| format | Article |
| id | doaj-art-31e59eff5cd448898cf9c5723194b881 |
| 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-31e59eff5cd448898cf9c5723194b8812025-01-30T00:00:16ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01183973398810.1109/JSTARS.2025.352722610836746ViT-ISRGAN: A High-Quality Super-Resolution Reconstruction Method for Multispectral Remote Sensing ImagesYifeng Yang0https://orcid.org/0009-0001-6018-6690Hengqian Zhao1https://orcid.org/0000-0003-0776-142XXiadan Huangfu2Zihan Li3Pan Wang4https://orcid.org/0000-0003-2846-9882College of Geoscience and Surveying Engineering, China University of Mining and Technology, Beijing, ChinaCollege of Geoscience and Surveying Engineering, China University of Mining and Technology, Beijing, ChinaCollege of Geoscience and Surveying Engineering, China University of Mining and Technology, Beijing, ChinaCollege of Geoscience and Surveying Engineering, China University of Mining and Technology, Beijing, ChinaCollege of Geoscience and Surveying Engineering, China University of Mining and Technology, Beijing, ChinaThe reflective characteristics of remote sensing image information depend on the scale of the observed area, with high-resolution images providing more detailed feature information. Currently, monitoring refined industries and extracting regional information necessitate higher-resolution remote sensing images. Super-resolution reconstruction of remote sensing multispectral images not only enhances the spatial resolution of these images but also preserves and improves the spectral information of multispectral data, thereby providing richer ground object information and more accurate environmental monitoring data. To improve the effectiveness of feature extraction in the generator network while maintaining model efficiency, this article proposes the vision transformer improved super-resolution generative adversarial network (ViT-ISRGAN) model. This model is an improvement upon the original SRGAN super-resolution image reconstruction method, incorporating lightweight network modules, channel attention modules, spatial-spectral residual attention, and the vision transformer structure. The ViT-ISRGAN model focuses on reconstructing four types of typical ground objects based on Sentinel-2 images: urban, water, farmland, and forest. Results indicate that the ViT-ISRGAN model excels in capturing texture details and color restoration, effectively extracting spectral and texture information from multispectral remote sensing images across various scenes. Compared to other super-resolution (SR) models, this approach demonstrates superior effectiveness and performance in the SR tasks of remote sensing multispectral images.https://ieeexplore.ieee.org/document/10836746/Downscalingremote sensingsuper-resolution (SR)transformervision transformer improved super-resolution generative adversarial network (ViT-ISRGAN) model |
| spellingShingle | Yifeng Yang Hengqian Zhao Xiadan Huangfu Zihan Li Pan Wang ViT-ISRGAN: A High-Quality Super-Resolution Reconstruction Method for Multispectral Remote Sensing Images IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Downscaling remote sensing super-resolution (SR) transformer vision transformer improved super-resolution generative adversarial network (ViT-ISRGAN) model |
| title | ViT-ISRGAN: A High-Quality Super-Resolution Reconstruction Method for Multispectral Remote Sensing Images |
| title_full | ViT-ISRGAN: A High-Quality Super-Resolution Reconstruction Method for Multispectral Remote Sensing Images |
| title_fullStr | ViT-ISRGAN: A High-Quality Super-Resolution Reconstruction Method for Multispectral Remote Sensing Images |
| title_full_unstemmed | ViT-ISRGAN: A High-Quality Super-Resolution Reconstruction Method for Multispectral Remote Sensing Images |
| title_short | ViT-ISRGAN: A High-Quality Super-Resolution Reconstruction Method for Multispectral Remote Sensing Images |
| title_sort | vit isrgan a high quality super resolution reconstruction method for multispectral remote sensing images |
| topic | Downscaling remote sensing super-resolution (SR) transformer vision transformer improved super-resolution generative adversarial network (ViT-ISRGAN) model |
| url | https://ieeexplore.ieee.org/document/10836746/ |
| work_keys_str_mv | AT yifengyang vitisrganahighqualitysuperresolutionreconstructionmethodformultispectralremotesensingimages AT hengqianzhao vitisrganahighqualitysuperresolutionreconstructionmethodformultispectralremotesensingimages AT xiadanhuangfu vitisrganahighqualitysuperresolutionreconstructionmethodformultispectralremotesensingimages AT zihanli vitisrganahighqualitysuperresolutionreconstructionmethodformultispectralremotesensingimages AT panwang vitisrganahighqualitysuperresolutionreconstructionmethodformultispectralremotesensingimages |