Hyperspectral Superresolution Reconstruction via Decomposition of Low-Rank and Sparse Tensor
Hyperspectral superresolution reconstruction technique obtains a high-resolution hyperspectral image (HR-HSI) by fusing both a low-resolution hyperspectral image (LR-HSI) and a high-resolution multispectral image. Existing methods of hyperspectral superresolution reconstruction are mostly concentrat...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9919351/ |
| _version_ | 1811338308257579008 |
|---|---|
| author | Huajing Wu Kefei Zhang Suqin Wu Minghao Zhang Shuangshuang Shi |
| author_facet | Huajing Wu Kefei Zhang Suqin Wu Minghao Zhang Shuangshuang Shi |
| author_sort | Huajing Wu |
| collection | DOAJ |
| description | Hyperspectral superresolution reconstruction technique obtains a high-resolution hyperspectral image (HR-HSI) by fusing both a low-resolution hyperspectral image (LR-HSI) and a high-resolution multispectral image. Existing methods of hyperspectral superresolution reconstruction are mostly concentrated on the global low-rank property while spatial and spectral information in individual regions is not considered. To address this issue, the decomposition of low-rank and sparse tensor is proposed in this study. First, HR-HSI was decomposed into low-rank and sparse components. The former was further separated into spatial and spectral domains according to the spectral low-rank property, and the latter was used to compensate for information loss caused by the low-rank property. Then, a nonlocal constraint of adaptive manifold extracting structural details by the manifold structure was designed to enforce nonlocal self-similarity of the spatial domain. In order to ensure the same spatial structure of different bands and reduce the false individual regions in the sparse component, a surface-aware regularization combined with group sparsity was utilized. Finally, HR-HSI was constructed by the alternating direction method of multipliers. Experiment results on three datasets show that the proposed method outperforms five common existing methods by means of both visual and quantitative evaluations. It is concluded that the new method by taking into account the low-rank and sparse properties can improve the result of the reconstruction. |
| first_indexed | 2024-04-13T18:08:59Z |
| format | Article |
| id | doaj.art-223e0e9d8a614686848e05c5cd326aed |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-04-13T18:08:59Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-223e0e9d8a614686848e05c5cd326aed2022-12-22T02:35:58ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01158943895710.1109/JSTARS.2022.32146539919351Hyperspectral Superresolution Reconstruction via Decomposition of Low-Rank and Sparse TensorHuajing Wu0https://orcid.org/0000-0002-7248-680XKefei Zhang1https://orcid.org/0000-0001-9376-1148Suqin Wu2https://orcid.org/0000-0002-0994-402XMinghao Zhang3https://orcid.org/0000-0002-5786-7436Shuangshuang Shi4https://orcid.org/0000-0001-6829-412XSchool of Environment Science and Spatial Informatics, China University of Mining and Technology, Xuzhou, ChinaSchool of Environment Science and Spatial Informatics, China University of Mining and Technology, Xuzhou, ChinaSchool of Environment Science and Spatial Informatics, China University of Mining and Technology, Xuzhou, ChinaSchool of Environment Science and Spatial Informatics, China University of Mining and Technology, Xuzhou, ChinaSchool of Environment Science and Spatial Informatics, China University of Mining and Technology, Xuzhou, ChinaHyperspectral superresolution reconstruction technique obtains a high-resolution hyperspectral image (HR-HSI) by fusing both a low-resolution hyperspectral image (LR-HSI) and a high-resolution multispectral image. Existing methods of hyperspectral superresolution reconstruction are mostly concentrated on the global low-rank property while spatial and spectral information in individual regions is not considered. To address this issue, the decomposition of low-rank and sparse tensor is proposed in this study. First, HR-HSI was decomposed into low-rank and sparse components. The former was further separated into spatial and spectral domains according to the spectral low-rank property, and the latter was used to compensate for information loss caused by the low-rank property. Then, a nonlocal constraint of adaptive manifold extracting structural details by the manifold structure was designed to enforce nonlocal self-similarity of the spatial domain. In order to ensure the same spatial structure of different bands and reduce the false individual regions in the sparse component, a surface-aware regularization combined with group sparsity was utilized. Finally, HR-HSI was constructed by the alternating direction method of multipliers. Experiment results on three datasets show that the proposed method outperforms five common existing methods by means of both visual and quantitative evaluations. It is concluded that the new method by taking into account the low-rank and sparse properties can improve the result of the reconstruction.https://ieeexplore.ieee.org/document/9919351/Adaptive manifoldhyperspectral superresolu- tion reconstructionnonlocal self-similarity |
| spellingShingle | Huajing Wu Kefei Zhang Suqin Wu Minghao Zhang Shuangshuang Shi Hyperspectral Superresolution Reconstruction via Decomposition of Low-Rank and Sparse Tensor IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Adaptive manifold hyperspectral superresolu- tion reconstruction nonlocal self-similarity |
| title | Hyperspectral Superresolution Reconstruction via Decomposition of Low-Rank and Sparse Tensor |
| title_full | Hyperspectral Superresolution Reconstruction via Decomposition of Low-Rank and Sparse Tensor |
| title_fullStr | Hyperspectral Superresolution Reconstruction via Decomposition of Low-Rank and Sparse Tensor |
| title_full_unstemmed | Hyperspectral Superresolution Reconstruction via Decomposition of Low-Rank and Sparse Tensor |
| title_short | Hyperspectral Superresolution Reconstruction via Decomposition of Low-Rank and Sparse Tensor |
| title_sort | hyperspectral superresolution reconstruction via decomposition of low rank and sparse tensor |
| topic | Adaptive manifold hyperspectral superresolu- tion reconstruction nonlocal self-similarity |
| url | https://ieeexplore.ieee.org/document/9919351/ |
| work_keys_str_mv | AT huajingwu hyperspectralsuperresolutionreconstructionviadecompositionoflowrankandsparsetensor AT kefeizhang hyperspectralsuperresolutionreconstructionviadecompositionoflowrankandsparsetensor AT suqinwu hyperspectralsuperresolutionreconstructionviadecompositionoflowrankandsparsetensor AT minghaozhang hyperspectralsuperresolutionreconstructionviadecompositionoflowrankandsparsetensor AT shuangshuangshi hyperspectralsuperresolutionreconstructionviadecompositionoflowrankandsparsetensor |