Spatial-spectral dual path hyperspectral image super-resolution reconstruction network based on spectral response functions
Recently, hyperspectral image (HSI) super-resolution (SR) techniques based on deep learning have been actively developed. However, most hyperspectral image super-resolution reconstruction methods usually use all spectral bands simultaneously, leading to a mismatch of spectral properties between reco...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-12-01
|
| Series: | Geocarto International |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/10106049.2022.2157497 |
| _version_ | 1811153898448093184 |
|---|---|
| author | Yinghao Xu Xi Jiang Junyi Hou Yuanyuan Sun Xijun Zhu |
| author_facet | Yinghao Xu Xi Jiang Junyi Hou Yuanyuan Sun Xijun Zhu |
| author_sort | Yinghao Xu |
| collection | DOAJ |
| description | Recently, hyperspectral image (HSI) super-resolution (SR) techniques based on deep learning have been actively developed. However, most hyperspectral image super-resolution reconstruction methods usually use all spectral bands simultaneously, leading to a mismatch of spectral properties between reconstructed HSI bands. Therefore, we proposed a new method of spatial-spectral dual path residual network (SGDPRN) based on spectral response function (SRF) to address the above problem. The SGDPRN is composed of the SRF guided grouping part, the spatial-spectral feature extraction part, and the final reconstruction part. Firstly, the reconstructed features for different spectral ranges are identified separately using SRF as a guide. Then, based on the grouping results, a spatial-spectral dual-path residual block is used to explore the spatial and spectral features by the designed parallel structure simultaneously. The spatial path is designed to extract sharp edges and realistic textures, and the spectral path is designed to model inter-spectral correlations to refine spectral features. At last, the third block of SGDPRN concatenates features of all groups and finishes the reconstruction of HSISR. QUST-1 satellite images have been applied in experiments, and the results showed that SGDPRN produced a higher peak signal to noise ratio, structural similarity metric, correlation coefficient, and lower spectral angle mapper, root mean square error than the other methods. This demonstrates that our method can effectively maintain the correlation of spectral bands while improving the spatial resolution. |
| first_indexed | 2024-03-11T23:46:59Z |
| format | Article |
| id | doaj.art-573e9f9316c7434fb101aa134a0ec2f5 |
| institution | Directory Open Access Journal |
| issn | 1010-6049 1752-0762 |
| language | English |
| last_indexed | 2024-03-11T23:46:59Z |
| publishDate | 2023-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Geocarto International |
| spelling | doaj.art-573e9f9316c7434fb101aa134a0ec2f52023-09-19T09:13:17ZengTaylor & Francis GroupGeocarto International1010-60491752-07622023-12-0138110.1080/10106049.2022.21574972157497Spatial-spectral dual path hyperspectral image super-resolution reconstruction network based on spectral response functionsYinghao Xu0Xi Jiang1Junyi Hou2Yuanyuan Sun3Xijun Zhu4College of Information Science and Technology, Qingdao University of Science and TechnologyCollege of Information Science and Technology, Qingdao University of Science and TechnologyCollege of Information Science and Technology, Qingdao University of Science and TechnologyCollege of Information Science and Technology, Qingdao University of Science and TechnologyCollege of Information Science and Technology, Qingdao University of Science and TechnologyRecently, hyperspectral image (HSI) super-resolution (SR) techniques based on deep learning have been actively developed. However, most hyperspectral image super-resolution reconstruction methods usually use all spectral bands simultaneously, leading to a mismatch of spectral properties between reconstructed HSI bands. Therefore, we proposed a new method of spatial-spectral dual path residual network (SGDPRN) based on spectral response function (SRF) to address the above problem. The SGDPRN is composed of the SRF guided grouping part, the spatial-spectral feature extraction part, and the final reconstruction part. Firstly, the reconstructed features for different spectral ranges are identified separately using SRF as a guide. Then, based on the grouping results, a spatial-spectral dual-path residual block is used to explore the spatial and spectral features by the designed parallel structure simultaneously. The spatial path is designed to extract sharp edges and realistic textures, and the spectral path is designed to model inter-spectral correlations to refine spectral features. At last, the third block of SGDPRN concatenates features of all groups and finishes the reconstruction of HSISR. QUST-1 satellite images have been applied in experiments, and the results showed that SGDPRN produced a higher peak signal to noise ratio, structural similarity metric, correlation coefficient, and lower spectral angle mapper, root mean square error than the other methods. This demonstrates that our method can effectively maintain the correlation of spectral bands while improving the spatial resolution.http://dx.doi.org/10.1080/10106049.2022.2157497super-resolutionspectral response functionhyperspectral imagesspectral dimensional attentiongroup convolution |
| spellingShingle | Yinghao Xu Xi Jiang Junyi Hou Yuanyuan Sun Xijun Zhu Spatial-spectral dual path hyperspectral image super-resolution reconstruction network based on spectral response functions Geocarto International super-resolution spectral response function hyperspectral images spectral dimensional attention group convolution |
| title | Spatial-spectral dual path hyperspectral image super-resolution reconstruction network based on spectral response functions |
| title_full | Spatial-spectral dual path hyperspectral image super-resolution reconstruction network based on spectral response functions |
| title_fullStr | Spatial-spectral dual path hyperspectral image super-resolution reconstruction network based on spectral response functions |
| title_full_unstemmed | Spatial-spectral dual path hyperspectral image super-resolution reconstruction network based on spectral response functions |
| title_short | Spatial-spectral dual path hyperspectral image super-resolution reconstruction network based on spectral response functions |
| title_sort | spatial spectral dual path hyperspectral image super resolution reconstruction network based on spectral response functions |
| topic | super-resolution spectral response function hyperspectral images spectral dimensional attention group convolution |
| url | http://dx.doi.org/10.1080/10106049.2022.2157497 |
| work_keys_str_mv | AT yinghaoxu spatialspectraldualpathhyperspectralimagesuperresolutionreconstructionnetworkbasedonspectralresponsefunctions AT xijiang spatialspectraldualpathhyperspectralimagesuperresolutionreconstructionnetworkbasedonspectralresponsefunctions AT junyihou spatialspectraldualpathhyperspectralimagesuperresolutionreconstructionnetworkbasedonspectralresponsefunctions AT yuanyuansun spatialspectraldualpathhyperspectralimagesuperresolutionreconstructionnetworkbasedonspectralresponsefunctions AT xijunzhu spatialspectraldualpathhyperspectralimagesuperresolutionreconstructionnetworkbasedonspectralresponsefunctions |