SIA OpenIR  > 机器人学研究室
Hyperspectral Image Restoration Via Total Variation Regularized Low-Rank Tensor Decomposition
Wang Y(王尧)1; Peng, Jiangjun1; Zhao Q(赵谦)1; Leung, Yee2; Zhao XL(赵熙乐)3; Meng DY(孟德宇)1,4
Department机器人学研究室
Source PublicationIEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
ISSN1939-1404
2018
Volume11Issue:4Pages:1227-1243
Indexed BySCI ; EI
EI Accession number20180104604831
WOS IDWOS:000429956000018
Contribution Rank4
Funding OrganizationNational Natural Science Foundation of China ; Vice-Chancellor's Discretionary Fund of the Chinese University of Hong Kong
KeywordHyperspectral Image (Hsi) Low-rank Tensor Decomposition Mixed Noise Total Variation (Tv)
Abstract

Hyperspectral images (HSIs) are often corrupted by a mixture of several types of noise during the acquisition process, e.g., Gaussian noise, impulse noise, dead lines, stripes, etc. Such complex noise could degrade the quality of the acquired HSIs, limiting the precision of the subsequent processing. In this paper, we present a novel tensor-based HSI restoration approach by fully identifying the intrinsic structures of the clean HSI part and the mixed noise part. Specifically, for the clean HSI part, we use tensor Tucker decomposition to describe the global correlation among all bands, and an anisotropic spatial-spectral total variation regularization to characterize the piecewise smooth structure in both spatial and spectral domains. For the mixed noise part, we adopt the l(1) norm regularization to detect the sparse noise, including stripes, impulse noise, and dead pixels. Despite that TV regularization has the ability of removing Gaussian noise, the Frobenius norm term is further used to model heavy Gaussian noise for some real-world scenarios. Then, we develop an efficient algorithm for solving the resulting optimization problem by using the augmented Lagrange multiplier method. Finally, extensive experiments on simulated and real-world noisy HSIs are carried out to demonstrate the superiority of the proposed method over the existing state-of-the-art ones.

Language英语
WOS SubjectEngineering, Electrical & Electronic ; Geography, Physical ; Remote Sensing ; Imaging Science & Photographic Technology
WOS KeywordNUCLEAR NORM MINIMIZATION ; TOTAL VARIATION MODEL ; NOISE-REDUCTION ; MATRIX RECOVERY ; SPARSE REPRESENTATION ; CLASSIFICATION
WOS Research AreaEngineering ; Physical Geography ; Remote Sensing ; Imaging Science & Photographic Technology
Funding ProjectNational Natural Science Foundation of China[11501440] ; National Natural Science Foundation of China[61603292] ; National Natural Science Foundation of China[61673015] ; National Natural Science Foundation of China[61373114] ; National Natural Science Foundation of China[61402082] ; National Natural Science Foundation of China[61772003] ; Vice-Chancellor's Discretionary Fund of the Chinese University of Hong Kong
Citation statistics
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/21888
Collection机器人学研究室
Corresponding AuthorZhao Q(赵谦)
Affiliation1.School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an 710049, China;
2.Institute of Future Cities, The Chinese University of Hong Kong, Shatin, Hong Kong, SAR;
3.School of Mathematical Sciences, University of Electronic Science and Technology of China, Chengdu 610054, China;
4.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
Recommended Citation
GB/T 7714
Wang Y,Peng, Jiangjun,Zhao Q,et al. Hyperspectral Image Restoration Via Total Variation Regularized Low-Rank Tensor Decomposition[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,2018,11(4):1227-1243.
APA Wang Y,Peng, Jiangjun,Zhao Q,Leung, Yee,Zhao XL,&Meng DY.(2018).Hyperspectral Image Restoration Via Total Variation Regularized Low-Rank Tensor Decomposition.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,11(4),1227-1243.
MLA Wang Y,et al."Hyperspectral Image Restoration Via Total Variation Regularized Low-Rank Tensor Decomposition".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 11.4(2018):1227-1243.
Files in This Item: Download All
File Name/Size DocType Version Access License
Hyperspectral Image (2500KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang Y(王尧)]'s Articles
[Peng, Jiangjun]'s Articles
[Zhao Q(赵谦)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang Y(王尧)]'s Articles
[Peng, Jiangjun]'s Articles
[Zhao Q(赵谦)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang Y(王尧)]'s Articles
[Peng, Jiangjun]'s Articles
[Zhao Q(赵谦)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Hyperspectral Image Restoration Via Total Variation Regularized Low-Rank Tensor Decomposition.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.