Journal article
Hyperspectral Image Recovery Using Nonconvex Sparsity and Low-Rank Regularizations
IEEE transactions on geoscience and remote sensing, Vol.58(1), pp.532-545
01/2020
DOI: 10.1109/TGRS.2019.2937901
Abstract
Hyperspectral image (HSI) restoration is an important preprocessing step in HSI data analysis to improve the image quality for subsequent applications of HSI. In this article, we introduce a spatial-spectral patch-based nonconvex sparsity and low-rank regularization method for HSI restoration. In contrast to traditional approaches based on convex penalties or nonconvex spectral penalty alone, we consider the sparsity of HSI in the spatial-spectral domain and combine the nonconvex low-rank penalty and the nonconvex 3-D total variation (TV)-like sparsity regularization to fully exploit the correlations in both spatial-spectral dimensions of the HSI data set. In addition, we propose a fast iterative variable splitting-based algorithm to effectively solve the corresponding optimization problem. Numerical experiments on both simulated and real HSI data sets demonstrate that the proposed nonconvex low-rank and TV (NonLRTV) method significantly improves the recovered image quality compared with the state-of-the-art algorithms.
Details
- Title: Subtitle
- Hyperspectral Image Recovery Using Nonconvex Sparsity and Low-Rank Regularizations
- Creators
- Yue Hu - School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, ChinaXiaodi Li - School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, ChinaYanfeng Gu - School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, ChinaMathews Jacob - Department of Electrical and Computer Engineering, University of Iowa, Iowa, IA, USA
- Resource Type
- Journal article
- Publication Details
- IEEE transactions on geoscience and remote sensing, Vol.58(1), pp.532-545
- Publisher
- IEEE
- DOI
- 10.1109/TGRS.2019.2937901
- ISSN
- 0196-2892
- eISSN
- 1558-0644
- Grant note
- 61871159 / National Natural Science Foundation of China (10.13039/501100001809) 61720106002 / National Natural Science Foundation of China (10.13039/501100001809) Harbin Institute of Technology (10.13039/501100003472) F2016018 / Natural Science Foundation of Heilongjiang Province (10.13039/501100005046)
- Language
- English
- Date published
- 01/2020
- Academic Unit
- Radiation Oncology; Electrical and Computer Engineering; Roy J. Carver Department of Biomedical Engineering; Radiology; Iowa Neuroscience Institute
- Record Identifier
- 9984066108902771
Metrics
19 Record Views