Hyperspectral Image Restoration via Global L1-2 Spatial–Spectral Total Variation Regularized Local Low-Rank Tensor Recovery
| Autor: | Hanping Yin, Xiaozhen Xie, Haijin Zeng, Haojie Cui, Jifeng Ning |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Rank (linear algebra)
Noise reduction 0211 other engineering and technologies 02 engineering and technology Impulse noise Regularization (mathematics) symbols.namesake Noise Gaussian noise symbols General Earth and Planetary Sciences Electrical and Electronic Engineering Algorithm Image restoration 021101 geological & geomatics engineering Mathematics Sparse matrix |
| Zdroj: | IEEE Transactions on Geoscience and Remote Sensing. 59:3309-3325 |
| ISSN: | 1558-0644 0196-2892 |
| DOI: | 10.1109/tgrs.2020.3007945 |
| Popis: | 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 $L_{1-2}$ nonconvex metric in image sparse structure exploitation, we first develop a 3-D $L_{1-2}$ spatial–spectral total variation ( $L_{1-2}$ 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 $L_{1-2}$ SSTV regularization and local LTR model, we propose a $L_{1-2}$ 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|