基于鲁棒低秩张量恢复的高光谱图像去噪

doi:10.11896/jsjkx.210200103

计算机科学 ›› 2021, Vol. 48 ›› Issue (11A): 303-307.doi: 10.11896/jsjkx.210200103

• 图像处理& 多媒体技术 • 上一篇下一篇

基于鲁棒低秩张量恢复的高光谱图像去噪

巫勇^1,2, 刘永坚¹, 唐瑭², 王洪林², 郑建成²

1 武汉理工大学计算机科学与技术学院武汉430010
2 空军预警学院雷达士官学校武汉430010

出版日期:2021-11-10 发布日期:2021-11-12
通讯作者: 巫勇(1982182410@qq.com)
基金资助:
国家自然科学基金(61401504)

Hyperspectral Image Denoising Based on Robust Low Rank Tensor Restoration

WU Yong^1,2, LIU Yong-jian¹, TANG Tang², WANG Hong-lin², ZHENG Jian-cheng²

1 School of Computer Science and Technology,Wuhan University of Technology,Wuhan 430010,China
2 Radar Sergeant School of Air force Early Warning Academy,Wuhan 430010,China

Online:2021-11-10 Published:2021-11-12
About author:WU Yong,born in 1982,postgraduate,master candidate,intermediate title.His main research interests include image processing and object recognition,etc.
Supported by:
National Natural Science Foundation of China(61401504).

摘要/Abstract

摘要： 去噪是高光谱图像进一步分析的重要预处理步骤,许多去噪方法都被用于高光谱图像数据立方体的去噪。然而,传统的去噪方法对异常值和非高斯噪声很敏感。文中利用底层干净HSI的张量性质数据、异常值的稀疏性质和非高斯噪声,提出一个新的基于鲁棒低秩张量修复的模型,从而在保护HSI的同时删除离散值的全局结构和不同类型的噪声(高斯噪声、脉冲噪声、死线等)。该模型可以用非精确增广拉格朗日法求解,仿真和真实高光谱图像实验的结果表明,该方法对HSI去噪是有效的。

关键词: HSI去噪, 低秩张量, 高光谱图像去噪, 高斯噪声, 脉冲噪声

Abstract: Denoising is an important preprocessing step to further analyze the hyperspectral image (HSI),and many denoising methods have been used for the denoising of the HSI data cube.However,the traditional denoising methods are sensitive to outliers and non-Gaussian noise.In this paper,by making using of the low-rank tensor property of the clean HSI data and the sparsity property of the outliers and non-Gaussian noise,we propose a new model based on the robust low-rank tensor recovery,which can retain the global structure of HSI and clean the outliers and mixed noise.The proposed model can be solved by the inexact augmented Lagrangian method.Experiments on simulated and real hyperspectral data show that the proposed algorithm is efficient for HSI restoration.

Key words: Gaussian noise, HSI denoising, Hyperspectral image denoising, Impulsive noise, Low-rank tensor

中图分类号:

TP751

巫勇, 刘永坚, 唐瑭, 王洪林, 郑建成. 基于鲁棒低秩张量恢复的高光谱图像去噪[J]. 计算机科学, 2021, 48(11A): 303-307. https://doi.org/10.11896/jsjkx.210200103

WU Yong, LIU Yong-jian, TANG Tang, WANG Hong-lin, ZHENG Jian-cheng. Hyperspectral Image Denoising Based on Robust Low Rank Tensor Restoration[J]. Computer Science, 2021, 48(11A): 303-307. https://doi.org/10.11896/jsjkx.210200103

参考文献

[1]ZHAO Y Q,YANG J X.Hyperspectral Image Denoising viaSparse Representation and Low-Rank Constraint[J].IEEE Transactions on Geoscience and Remote Sensing,2015,53(1):296-308.
[2]WANG Z P,TYO J S,HAYAT M M.Generalized Signal-to-Noise Ratio for Spectral Sensors with Correlated Bands[J].Journal of The Optical Society of America A,2008,25(10):2528-2534.
[3]ZHANG L F,ZHANG L P,TAO D C,et al.Compression of Hyperspectral Remote Sensing Images by Tensor Approach[J].Neurocomputing,2015,147:358-363.
[4]ZHANG H Y,HE W,ZHANGL P,et al.Hyperspectral Image Restoration Using Low-Rank Matrix Recovery[J].IEEE transactions on geoscience and remote sensing,2013,52(8):4729-4743.
[5]GUO X,HUANG X,ZHANG L P,et al.Hyperspectral Image Noise Reduction Based on Rank-1 Tensor Decomposition[J].ISPRS Journal of Photogrammetry and Remote Sensing,2013,83:50-63.
[6]MA J Y,ZHAO J,TIANJ W,et al.Robust Point Matching via Vector Field Consensus[J].IEEE Transactions on Image Processing.2014,23(4):1706-1721.
[7]YUAN Q Q,ZHANG L P,SHEN H F.Hyperspectral Image Denoising with A Spatial-Spectral View Fusion Strategy[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(5):2314-2325.
[8]LIN T,BOURENNANE S.Survey of Hyperspectral Image Denoising Methods Based on Tensor Decompositions[J].EURASIP journal on Advances in Signal Processing,2013,186(1):1-11.
[9]MUTI D,BOURENNANE S,MAROT J.Lower-Rank Tensor Approximation and Multiway Filtering[J].SIAM Journal on Matrix Analysis and Applications,2008,30(3):1172-1204.
[10]RENARD N,BOURENNANE S,BLANC-TALON J.Denoising and Dimensionality Reduction Using Multilinear Tools for Hyperspectral Images[J].IEEE Geoscience and Remote Sensing Letters,2008,5(2):138-142.
[11]LIU X F,BOURENNANE S,FOSSATI C.Denoising of Hyperspectral Images Using the PARAFAC Model and Statistical Performance Analysis[J].IEEE Transactions on Geoscience and Remote Sensing,2012,50(10):3717-3724.
[12]LIN T,BOURENNANE S.Hyperspectral Image Processing by Jointly Filtering Wavelet Component Tensor[J].IEEE Transactions on Geoscience and Remote Sensing,2013,51(6):3529-3541.
[13]LI Q,LI H Q,LU Z B,et al.Denoising of Hyperspectral Images Employing Two-Phase Matrix Decomposition[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(9):3742-3754.
[14]GOLDFARB D,QIN Z W.Robust Low-Rank Tensor Recovery:Models and Algorithms[J].SIAM Journal on Matrix Analysis and Applications,2014,35(1):225-253.
[15]WRIGHT J,GANESH A,RAO S,et al.Robust Principal Component Analysis:Exact Recovery of Corrupted Low-Rank Matrices via Convex Optimization[R].Coordinated Science Laboratory Report no.UILU-ENG-09-2210,DC-243,2009.
[16]GANDY S,RECHT B,YAMADA I.Tensor Completion andLow-n-Rank Tensor Recovery via Convex Optimization[J].Inverse Problems,2011,27(2):1-19.
[17]LIU G,LIN Z,YAN S,et al.Robust Recovery of SubspaceStructures by Low-Rank Representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(1):171-184.
[18]LIN Z C,CHEN M M,WU L,et al.The Augmented Lagrange Multiplier Method for Exact recovery of Corrupted Low-Rank Matrices[R].UIUC Tech.Rep.UILU-ENG-09-2215 (University Illinois at Urbana Champaign,Champaign,Illinois,2009).
[19]ZHANG Y.Recent advances in alternating direction methods:practice and theory[R].Presented at IPAM Workshop:Numerical Methods for Continuous Optimization.Los Angeles,California,2010.
[20]ZHANG L,ZHANG L,MOU X Q,et al.FSIM:A Feature Similarity Index for Image Quality Assessment[J].IEEE Transactions on Image Processing,2011,20(8):2378-2386.
[21]DABOV K,FOI A,EGIAZARIAN K.Video Denoising bySparse 3D Transform-Domain Collaborative Filtering[C]//Proceedings of 15th European Signal Processing Conference.Pozna'n,Poland,2007.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于鲁棒低秩张量恢复的高光谱图像去噪

Hyperspectral Image Denoising Based on Robust Low Rank Tensor Restoration

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

Metrics

本文评价

推荐阅读 0

[1]	郑建炜, 黄娟娟, 秦梦洁, 徐宏辉, 刘志. 基于非局部相似及加权截断核范数的高光谱图像去噪 Hyperspectral Image Denoising Based on Non-local Similarity and Weighted-truncated NuclearNorm 计算机科学, 2021, 48(9): 160-167. https://doi.org/10.11896/jsjkx.200600135
[2]	林云, 黄桢航, 高凡. 扩散式变阶数最大相关熵准则算法 Diffusion Variable Tap-length Maximum Correntropy Criterion Algorithm 计算机科学, 2021, 48(5): 263-269. https://doi.org/10.11896/jsjkx.200300043
[3]	郭远华,周贤林. 基于灰度密度和四方向的随机脉冲噪声检测 Random-valued Impulse Noise Detection Based on Pixel-valued Density and Four Directions 计算机科学, 2016, 43(Z11): 220-222. https://doi.org/10.11896/j.issn.1002-137X.2016.11A.050
[4]	罗海驰,李岳阳,孙俊. 一种基于自适应神经模糊推理系统的图像滤波方法 Filtering Method for Images Based on Adaptive Neuro-fuzzy Inference System 计算机科学, 2013, 40(7): 302-306.