Hyperspectral Image Denoising Based on Nonlocal Low-Rank and TV Regularization
Open Access
- 17 June 2020
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 12 (12), 1956
- https://doi.org/10.3390/rs12121956
Abstract
Hyperspectral image (HSI) acquisitions are degraded by various noises, among which additive Gaussian noise may be the worst-case, as suggested by information theory. In this paper, we present a novel tensor-based HSI denoising approach by fully identifying the intrinsic structures of the clean HSI and the noise. Specifically, the HSI is first divided into local overlapping full-band patches (FBPs), then the nonlocal similar patches in each group are unfolded and stacked into a new third order tensor. As this tensor shows a stronger low-rank property than the original degraded HSI, the tensor weighted nuclear norm minimization (TWNNM) on the constructed tensor can effectively separate the low-rank clean HSI patches. In addition, a regularization strategy with spatial–spectral total variation (SSTV) is utilized to ensure the global spatial–spectral smoothness in both spatial and spectral domains. Our method is designed to model the spatial–spectral non-local self-similarity and global spatial–spectral smoothness simultaneously. Experiments conducted on simulated and real datasets show the superiority of the proposed method.Keywords
Funding Information
- National Natural Science Foundation of China (61771391, 61371152)
This publication has 41 references indexed in Scilit:
- Hyperspectral and Multispectral Image Fusion via Graph Laplacian-Guided Coupled Tensor DecompositionIEEE Transactions on Geoscience and Remote Sensing, 2020
- Spectral Super-Resolution for Multispectral Image Based on Spectral Improvement Strategy and Spatial Preservation StrategyIEEE Transactions on Geoscience and Remote Sensing, 2019
- Hyper-Laplacian regularized nonlocal low-rank matrix recovery for hyperspectral image compressive sensing reconstructionInformation Sciences, 2019
- Nonlocal Tensor Sparse Representation and Low-Rank Regularization for Hyperspectral Image Compressive Sensing ReconstructionRemote Sensing, 2019
- Learning and Transferring Deep Joint Spectral–Spatial Features for Hyperspectral ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2017
- Total-Variation-Regularized Low-Rank Matrix Factorization for Hyperspectral Image RestorationIEEE Transactions on Geoscience and Remote Sensing, 2015
- Is Gaussian noise the worst-case additive noise in wireless networks?Published by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Hyperspectral Image Denoising Employing a Spectral–Spatial Adaptive Total Variation ModelIEEE Transactions on Geoscience and Remote Sensing, 2012
- Image Denoising Via Sparse and Redundant Representations Over Learned DictionariesIEEE Transactions on Image Processing, 2006
- Noise reduction of hyperspectral imagery using hybrid spatial-spectral derivative-domain wavelet shrinkageIEEE Transactions on Geoscience and Remote Sensing, 2006