Reconstruction of Hyperspectral Images From Spectral Compressed Sensing Based on a Multitype Mixing Model
Hyperspectral compressed sensing (HCS) based on spectral unmixing technique has shown great reconstruction performance. In particular, the linear mixed model (LMM) has been widely used in HCS reconstruction. However, due to the complexity of environmental conditions, instrumental configurations, and...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9094327/ |
id |
doaj-57fb7d6dcf2f432cb319e20ccca7a4d7 |
---|---|
record_format |
Article |
spelling |
doaj-57fb7d6dcf2f432cb319e20ccca7a4d72021-06-03T23:02:16ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352020-01-01132304232010.1109/JSTARS.2020.29943349094327Reconstruction of Hyperspectral Images From Spectral Compressed Sensing Based on a Multitype Mixing ModelZhongliang Wang0https://orcid.org/0000-0003-4525-5798Mi He1https://orcid.org/0000-0001-9983-8863Zhen Ye2Ke Xu3Yongjian Nian4https://orcid.org/0000-0001-6779-0850Bormin Huang5Department of Electric Engineering, Tongling University, Tongling, ChinaCollege of Biomedical Engineering and Imaging Medicine, Army Medical University (Third Military Medical University), Chongqing, ChinaSchool of Electronics and Control Engineering, Chang'an University, Xi'an, ChinaCollege of Electronic Science, National University of Defense and Technology, Changsha, ChinaCollege of Biomedical Engineering and Imaging Medicine, Army Medical University (Third Military Medical University), Chongqing, ChinaSchool of Information Science and Technology, Southwest Jiaotong University, Chengdu, ChinaHyperspectral compressed sensing (HCS) based on spectral unmixing technique has shown great reconstruction performance. In particular, the linear mixed model (LMM) has been widely used in HCS reconstruction. However, due to the complexity of environmental conditions, instrumental configurations, and material nonlinear mixing effects, LMM cannot accurately represent the hyperspectral images, which limits the improvement of reconstruction quality. In this article, first, by introducing spectral variability, nonlinear mixing, and residuals, a multitype mixed model (MMM) is proposed to establish a more accurate hyperspectral image model. Then, a novel MMM-based HCS is proposed, which performs spectral compressed sampling at the sampling stage only, and at the reconstruction stage, by using spectral unmixing, an MMM-based HCS super-resolution reconstruction algorithm from spectral compressed sensing data is developed, and the alternating direction multiplier method is employed to estimate each component of the MMM, furthermore, reasonable prior knowledge of each component is introduced to improve the estimation accuracy. Experimental results on hyperspectral datasets demonstrate that the proposed model outperforms those state-of-the-art methods based on the LMM in terms of HCS reconstruction quality.https://ieeexplore.ieee.org/document/9094327/Compressed sensinghyperspectral remote sensinglinear mixing model (LMM)spectral unmixing |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zhongliang Wang Mi He Zhen Ye Ke Xu Yongjian Nian Bormin Huang |
spellingShingle |
Zhongliang Wang Mi He Zhen Ye Ke Xu Yongjian Nian Bormin Huang Reconstruction of Hyperspectral Images From Spectral Compressed Sensing Based on a Multitype Mixing Model IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Compressed sensing hyperspectral remote sensing linear mixing model (LMM) spectral unmixing |
author_facet |
Zhongliang Wang Mi He Zhen Ye Ke Xu Yongjian Nian Bormin Huang |
author_sort |
Zhongliang Wang |
title |
Reconstruction of Hyperspectral Images From Spectral Compressed Sensing Based on a Multitype Mixing Model |
title_short |
Reconstruction of Hyperspectral Images From Spectral Compressed Sensing Based on a Multitype Mixing Model |
title_full |
Reconstruction of Hyperspectral Images From Spectral Compressed Sensing Based on a Multitype Mixing Model |
title_fullStr |
Reconstruction of Hyperspectral Images From Spectral Compressed Sensing Based on a Multitype Mixing Model |
title_full_unstemmed |
Reconstruction of Hyperspectral Images From Spectral Compressed Sensing Based on a Multitype Mixing Model |
title_sort |
reconstruction of hyperspectral images from spectral compressed sensing based on a multitype mixing model |
publisher |
IEEE |
series |
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
issn |
2151-1535 |
publishDate |
2020-01-01 |
description |
Hyperspectral compressed sensing (HCS) based on spectral unmixing technique has shown great reconstruction performance. In particular, the linear mixed model (LMM) has been widely used in HCS reconstruction. However, due to the complexity of environmental conditions, instrumental configurations, and material nonlinear mixing effects, LMM cannot accurately represent the hyperspectral images, which limits the improvement of reconstruction quality. In this article, first, by introducing spectral variability, nonlinear mixing, and residuals, a multitype mixed model (MMM) is proposed to establish a more accurate hyperspectral image model. Then, a novel MMM-based HCS is proposed, which performs spectral compressed sampling at the sampling stage only, and at the reconstruction stage, by using spectral unmixing, an MMM-based HCS super-resolution reconstruction algorithm from spectral compressed sensing data is developed, and the alternating direction multiplier method is employed to estimate each component of the MMM, furthermore, reasonable prior knowledge of each component is introduced to improve the estimation accuracy. Experimental results on hyperspectral datasets demonstrate that the proposed model outperforms those state-of-the-art methods based on the LMM in terms of HCS reconstruction quality. |
topic |
Compressed sensing hyperspectral remote sensing linear mixing model (LMM) spectral unmixing |
url |
https://ieeexplore.ieee.org/document/9094327/ |
work_keys_str_mv |
AT zhongliangwang reconstructionofhyperspectralimagesfromspectralcompressedsensingbasedonamultitypemixingmodel AT mihe reconstructionofhyperspectralimagesfromspectralcompressedsensingbasedonamultitypemixingmodel AT zhenye reconstructionofhyperspectralimagesfromspectralcompressedsensingbasedonamultitypemixingmodel AT kexu reconstructionofhyperspectralimagesfromspectralcompressedsensingbasedonamultitypemixingmodel AT yongjiannian reconstructionofhyperspectralimagesfromspectralcompressedsensingbasedonamultitypemixingmodel AT borminhuang reconstructionofhyperspectralimagesfromspectralcompressedsensingbasedonamultitypemixingmodel |
_version_ |
1721398784873725952 |