Hyperspectral Image Super-Resolution Based on Tensor Spatial-Spectral Joint Correlation Regularization
Compared with natural image super-resolution, hyperspectral image super-resolution (HSR) is more complex because the redundancy in spectral bands and spatial information. To overcome the difficulties exist in HSR, in this paper, we propose a tensor spatial-spectral joint correlation based HSR method...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9050714/ |
id |
doaj-5ac3904ebe814b989c45f5dedb4f706f |
---|---|
record_format |
Article |
spelling |
doaj-5ac3904ebe814b989c45f5dedb4f706f2021-03-30T01:36:08ZengIEEEIEEE Access2169-35362020-01-018636546366510.1109/ACCESS.2020.29824949050714Hyperspectral Image Super-Resolution Based on Tensor Spatial-Spectral Joint Correlation RegularizationYinghui Xing0https://orcid.org/0000-0001-6021-8261Shuyuan Yang1Licheng Jiao2https://orcid.org/0000-0003-3354-9617School of Artificial Intelligence, Xidian University, Xi’an, ChinaSchool of Artificial Intelligence, Xidian University, Xi’an, ChinaSchool of Artificial Intelligence, Xidian University, Xi’an, ChinaCompared with natural image super-resolution, hyperspectral image super-resolution (HSR) is more complex because the redundancy in spectral bands and spatial information. To overcome the difficulties exist in HSR, in this paper, we propose a tensor spatial-spectral joint correlation based HSR method. Start with the tensor representation, we construct a series of fourth-order tensors to preserve the intrinsic structure of hyperspectral images, and then explore the spatial-spectral joint correlation based on meaningful interpretations of tensor canonical matrices. To further constrain the spectral characteristics, we analyze the sparsity of the spectral gradients and model it with Laplacian prior. Then, the two regularizations are combined with the reconstruction model to develop a new HSR method. Finally, an iterative optimization algorithm based on alternating direction method of multiplier (ADMM) and augmented Lagrangian multiplier method is proposed to reconstruct the high-resolution hyperspectral images. Experimental results on several data sets illustrate the effectiveness of our proposed method both in visual and numerical comparisons.https://ieeexplore.ieee.org/document/9050714/Hyperspectral imagelow-rank analysisspatial-spectral joint correlationsuper-resolutiontensor decomposition |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yinghui Xing Shuyuan Yang Licheng Jiao |
spellingShingle |
Yinghui Xing Shuyuan Yang Licheng Jiao Hyperspectral Image Super-Resolution Based on Tensor Spatial-Spectral Joint Correlation Regularization IEEE Access Hyperspectral image low-rank analysis spatial-spectral joint correlation super-resolution tensor decomposition |
author_facet |
Yinghui Xing Shuyuan Yang Licheng Jiao |
author_sort |
Yinghui Xing |
title |
Hyperspectral Image Super-Resolution Based on Tensor Spatial-Spectral Joint Correlation Regularization |
title_short |
Hyperspectral Image Super-Resolution Based on Tensor Spatial-Spectral Joint Correlation Regularization |
title_full |
Hyperspectral Image Super-Resolution Based on Tensor Spatial-Spectral Joint Correlation Regularization |
title_fullStr |
Hyperspectral Image Super-Resolution Based on Tensor Spatial-Spectral Joint Correlation Regularization |
title_full_unstemmed |
Hyperspectral Image Super-Resolution Based on Tensor Spatial-Spectral Joint Correlation Regularization |
title_sort |
hyperspectral image super-resolution based on tensor spatial-spectral joint correlation regularization |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Compared with natural image super-resolution, hyperspectral image super-resolution (HSR) is more complex because the redundancy in spectral bands and spatial information. To overcome the difficulties exist in HSR, in this paper, we propose a tensor spatial-spectral joint correlation based HSR method. Start with the tensor representation, we construct a series of fourth-order tensors to preserve the intrinsic structure of hyperspectral images, and then explore the spatial-spectral joint correlation based on meaningful interpretations of tensor canonical matrices. To further constrain the spectral characteristics, we analyze the sparsity of the spectral gradients and model it with Laplacian prior. Then, the two regularizations are combined with the reconstruction model to develop a new HSR method. Finally, an iterative optimization algorithm based on alternating direction method of multiplier (ADMM) and augmented Lagrangian multiplier method is proposed to reconstruct the high-resolution hyperspectral images. Experimental results on several data sets illustrate the effectiveness of our proposed method both in visual and numerical comparisons. |
topic |
Hyperspectral image low-rank analysis spatial-spectral joint correlation super-resolution tensor decomposition |
url |
https://ieeexplore.ieee.org/document/9050714/ |
work_keys_str_mv |
AT yinghuixing hyperspectralimagesuperresolutionbasedontensorspatialspectraljointcorrelationregularization AT shuyuanyang hyperspectralimagesuperresolutionbasedontensorspatialspectraljointcorrelationregularization AT lichengjiao hyperspectralimagesuperresolutionbasedontensorspatialspectraljointcorrelationregularization |
_version_ |
1724186784335659008 |