Hyperspectral Image Restoration via Global L1-2 Spatial-Spectral Total Variation Regularized Local Low-Rank Tensor Recovery

Hyperspectral images (HSIs) are usually corrupted by various noises, e.g., Gaussian noise, impulse noise, stripes, dead lines, and many others. In this article, motivated by the good performance of the <inline-formula> <tex-math notation="LaTeX">L_{1-2} </tex-math></in...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on geoscience and remote sensing Vol. 59; no. 4; pp. 3309 - 3325
Main Authors: Zeng, Haijin, Xie, Xiaozhen, Cui, Haojie, Yin, Hanping, Ning, Jifeng
Format: Journal Article
Language:English
Published: New York IEEE 01.04.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Algorithms
Exploitation
Hyperspectral images (HSIs)
Hyperspectral imaging
Hyperspectral sensors
Image restoration
Iterative methods
L1-2 spatial–spectral total variation (L1-2SSTV)
local low-rank tensor recovery (LTR)
Mathematical analysis
mixed noise
Noise
Noise reduction
Random noise
Recovery
Regularization
Restoration
Singular value decomposition
Solid modeling
Sparse matrices
Tensile stress
Tensors
ISSN:0196-2892, 1558-0644
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Hyperspectral images (HSIs) are usually corrupted by various noises, e.g., Gaussian noise, impulse noise, stripes, dead lines, and many others. In this article, motivated by the good performance of the <inline-formula> <tex-math notation="LaTeX">L_{1-2} </tex-math></inline-formula> nonconvex metric in image sparse structure exploitation, we first develop a 3-D <inline-formula> <tex-math notation="LaTeX">L_{1-2} </tex-math></inline-formula> spatial-spectral total variation (<inline-formula> <tex-math notation="LaTeX">L_{1-2} </tex-math></inline-formula>SSTV) regularization to globally represent the sparse prior in the gradient domain of HSIs. Then, we divide HSIs into local overlapping 3-D patches, and low-rank tensor recovery (LTR) is locally used to effectively separate the low-rank clean HSI patches from complex noise. The patchwise LTR can not only adapt to the local low-rank property of HSIs well but also significantly reduce the information loss caused by the global LTR. Finally, integrating the advantages of both the global <inline-formula> <tex-math notation="LaTeX">L_{1-2} </tex-math></inline-formula>SSTV regularization and local LTR model, we propose a <inline-formula> <tex-math notation="LaTeX">L_{1-2} </tex-math></inline-formula>SSTV regularized local LTR model for hyperspectral restoration. In the framework of the alternating direction method of multipliers, the difference of convex algorithm, the split Bregman iteration method, and tensor singular value decomposition method are adopted to solve the proposed model efficiently. Simulated and real HSI experiments show that the proposed model can reduce the dependence on noise independent and identical distribution hypotheses, and simultaneously remove various types of noise, even structure-related noise.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2020.3007945