Hyperspectral Image Denoising With Total Variation Regularization and Nonlocal Low-Rank Tensor Decomposition
Hyperspectral Image Denoising With Total Variation Regularization and Nonlocal Low-Rank Tensor Decomposition
复制标题
采用全变分正则化和非局部低阶张量分解的高光谱图像去噪
DOI：
10.1109/tgrs.2019.2947333
复制
发表时间：
2020-05
影响因子：
8.2
通讯作者：
Liangpei Zhang
中科院分区：
文献类型：
--
作者：
Hongyan Zhang;Lu Liu;Wei He;Liangpei Zhang
高光谱图像通常会受到多种噪声的干扰，从而降低了图像的质量，限制了后续的应用。在这篇文章中，我们提出了一种新的去噪方法的HSI恢复任务相结合的非局部低秩张量分解和总变分正则化，我们称之为TV-NLRTD。为了同时捕获非局部相似性和高谱相关性，首先将HSI分割成重叠的3-D立方体，这些立方体通过<inline-formula><tex-math notation="LaTeX">$k$</tex-math></inline-formula>-means++算法分成几个集群，并通过低秩张量逼近来利用。然后研究空间谱全变分（SSTV）正则化，以从去噪重叠立方体恢复干净的HSI。同时，<inline-formula><tex-math notation="LaTeX">$\ell _{1} $</tex-math></inline-formula>-范数有利于分离干净的非局部低秩张量群和稀疏噪声。采用高效的交替方向乘子法（ADMM）对TV-NLRTD方法进行了优化。仿真和真实的高光谱数据集的实验结果表明，与现有的HSI去噪算法相比，该方法具有更好的去噪效果。
Hyperspectral images (HSIs) are normally corrupted by a mixture of various noise types, which degrades the quality of the acquired image and limits the subsequent application. In this article, we propose a novel denoising method for the HSI restoration task by combining nonlocal low-rank tensor decomposition and total variation regularization, which we refer to as TV-NLRTD. To simultaneously capture the nonlocal similarity and high spectral correlation, the HSI is first segmented into overlapping 3-D cubes that are grouped into several clusters by the <inline-formula> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula>-means++ algorithm and exploited by low-rank tensor approximation. Spatial–spectral total variation (SSTV) regularization is then investigated to restore the clean HSI from the denoised overlapping cubes. Meanwhile, the <inline-formula> <tex-math notation="LaTeX">$\ell _{1} $ </tex-math></inline-formula>-norm facilitates the separation of the clean nonlocal low-rank tensor groups and the sparse noise. The proposed TV-NLRTD method is optimized by employing the efficient alternating direction method of multipliers (ADMM) algorithm. The experimental results obtained with both simulated and real hyperspectral data sets confirm the validity and superiority of the proposed method compared with the current state-of-the-art HSI denoising algorithms.
登录
查看更多内容
DOI：
10.1109/jstars.2012.2194696
发表时间：
2012-04-01
影响因子：
5.5
作者：
Bioucas-Dias, Jose M.;Plaza, Antonio;Chanussot, Jocelyn
通讯作者：
Chanussot, Jocelyn
影响因子：
10.6
作者：
Ng, Michael K.;Wen, You-Wei;Huang, Yu-Mei
通讯作者：
Huang, Yu-Mei
DOI：
10.5194/isprsannals-i-7-95-2012
发表时间：
2012-07
期刊：
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
影响因子：
--
作者：
Hongyan Zhang
通讯作者：
Hongyan Zhang
DOI：
10.1109/cmvit.2017.22
发表时间：
2017-02
期刊：
2017 International Conference on Machine Vision and Information Technology (CMVIT)
影响因子：
--
作者：
Jize Xue;Yongqiang Zhao
通讯作者：
Jize Xue;Yongqiang Zhao
DOI：
10.1109/whispers.2013.8080674
发表时间：
2013-06
期刊：
2013 5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)
影响因子：
--
作者：
Jie Li;Huanfeng Shen;Qiangqiang Yuan;Liangpei Zhang;W. Gong
通讯作者：
Jie Li;Huanfeng Shen;Qiangqiang Yuan;Liangpei Zhang;W. Gong