Nonlocal Tensor Sparse Representation and Low-Rank Regularization for Hyperspectral Image Compressive Sensing Reconstruction
Hyperspectral image compressive sensing reconstruction (HSI-CSR) is an important issue in remote sensing, and has recently been investigated increasingly by the sparsity prior based approaches. However, most of the available HSI-CSR methods consider the sparsity prior in spatial and spectral vector...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-01-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | http://www.mdpi.com/2072-4292/11/2/193 |
id |
doaj-1d280a57133040bdad45f92a681f2447 |
---|---|
record_format |
Article |
spelling |
doaj-1d280a57133040bdad45f92a681f24472020-11-25T01:06:24ZengMDPI AGRemote Sensing2072-42922019-01-0111219310.3390/rs11020193rs11020193Nonlocal Tensor Sparse Representation and Low-Rank Regularization for Hyperspectral Image Compressive Sensing ReconstructionJize Xue0Yongqiang Zhao1Wenzhi Liao2Jonathan Cheung-Wai Chan3School of Automation, Northwestern Polytechnical University, Xi’an 710072, ChinaResearch & Development Institute of Northwestern Polytechnical University in Shenzhen, Shenzhen 518057, ChinaDepartment of Telecommunications and Information Processing, Ghent University-TELIN-IMEC, 9000 Ghent, BelgiumDepartment of Electronics and Informatics, Vrije, Universiteit Brussel, 1050 Brussel, BelgiumHyperspectral image compressive sensing reconstruction (HSI-CSR) is an important issue in remote sensing, and has recently been investigated increasingly by the sparsity prior based approaches. However, most of the available HSI-CSR methods consider the sparsity prior in spatial and spectral vector domains via vectorizing hyperspectral cubes along a certain dimension. Besides, in most previous works, little attention has been paid to exploiting the underlying nonlocal structure in spatial domain of the HSI. In this paper, we propose a nonlocal tensor sparse and low-rank regularization (NTSRLR) approach, which can encode essential structured sparsity of an HSI and explore its advantages for HSI-CSR task. Specifically, we study how to utilize reasonably the l 1 -based sparsity of core tensor and tensor nuclear norm function as tensor sparse and low-rank regularization, respectively, to describe the nonlocal spatial-spectral correlation hidden in an HSI. To study the minimization problem of the proposed algorithm, we design a fast implementation strategy based on the alternative direction multiplier method (ADMM) technique. Experimental results on various HSI datasets verify that the proposed HSI-CSR algorithm can significantly outperform existing state-of-the-art CSR techniques for HSI recovery.http://www.mdpi.com/2072-4292/11/2/193hyperspectral imagecompressive sensingstructured sparsitytensor sparse decompositiontensor low-rank approximation |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jize Xue Yongqiang Zhao Wenzhi Liao Jonathan Cheung-Wai Chan |
spellingShingle |
Jize Xue Yongqiang Zhao Wenzhi Liao Jonathan Cheung-Wai Chan Nonlocal Tensor Sparse Representation and Low-Rank Regularization for Hyperspectral Image Compressive Sensing Reconstruction Remote Sensing hyperspectral image compressive sensing structured sparsity tensor sparse decomposition tensor low-rank approximation |
author_facet |
Jize Xue Yongqiang Zhao Wenzhi Liao Jonathan Cheung-Wai Chan |
author_sort |
Jize Xue |
title |
Nonlocal Tensor Sparse Representation and Low-Rank Regularization for Hyperspectral Image Compressive Sensing Reconstruction |
title_short |
Nonlocal Tensor Sparse Representation and Low-Rank Regularization for Hyperspectral Image Compressive Sensing Reconstruction |
title_full |
Nonlocal Tensor Sparse Representation and Low-Rank Regularization for Hyperspectral Image Compressive Sensing Reconstruction |
title_fullStr |
Nonlocal Tensor Sparse Representation and Low-Rank Regularization for Hyperspectral Image Compressive Sensing Reconstruction |
title_full_unstemmed |
Nonlocal Tensor Sparse Representation and Low-Rank Regularization for Hyperspectral Image Compressive Sensing Reconstruction |
title_sort |
nonlocal tensor sparse representation and low-rank regularization for hyperspectral image compressive sensing reconstruction |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2019-01-01 |
description |
Hyperspectral image compressive sensing reconstruction (HSI-CSR) is an important issue in remote sensing, and has recently been investigated increasingly by the sparsity prior based approaches. However, most of the available HSI-CSR methods consider the sparsity prior in spatial and spectral vector domains via vectorizing hyperspectral cubes along a certain dimension. Besides, in most previous works, little attention has been paid to exploiting the underlying nonlocal structure in spatial domain of the HSI. In this paper, we propose a nonlocal tensor sparse and low-rank regularization (NTSRLR) approach, which can encode essential structured sparsity of an HSI and explore its advantages for HSI-CSR task. Specifically, we study how to utilize reasonably the l 1 -based sparsity of core tensor and tensor nuclear norm function as tensor sparse and low-rank regularization, respectively, to describe the nonlocal spatial-spectral correlation hidden in an HSI. To study the minimization problem of the proposed algorithm, we design a fast implementation strategy based on the alternative direction multiplier method (ADMM) technique. Experimental results on various HSI datasets verify that the proposed HSI-CSR algorithm can significantly outperform existing state-of-the-art CSR techniques for HSI recovery. |
topic |
hyperspectral image compressive sensing structured sparsity tensor sparse decomposition tensor low-rank approximation |
url |
http://www.mdpi.com/2072-4292/11/2/193 |
work_keys_str_mv |
AT jizexue nonlocaltensorsparserepresentationandlowrankregularizationforhyperspectralimagecompressivesensingreconstruction AT yongqiangzhao nonlocaltensorsparserepresentationandlowrankregularizationforhyperspectralimagecompressivesensingreconstruction AT wenzhiliao nonlocaltensorsparserepresentationandlowrankregularizationforhyperspectralimagecompressivesensingreconstruction AT jonathancheungwaichan nonlocaltensorsparserepresentationandlowrankregularizationforhyperspectralimagecompressivesensingreconstruction |
_version_ |
1725190475269275648 |