OPT OpenIR  > 光谱成像技术研究室
A Novel NMF Guided for Hyperspectral Unmixing From Incomplete and Noisy Data
Dong, Le1; Lu, Xiaoqiang2; Liu, Ganchao1; Yuan, Yuan1
作者部门光谱成像技术研究室
2022
发表期刊IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
ISSN0196-2892;1558-0644
卷号60
产权排序2
摘要

The nonnegative matrix factorization (NMF)-combined spatial-spectral information has been widely applied in the unmixing of hyperspectral images (HSIs). However, how to select the appropriate similarity pixels and explore the spatial information and how to adapt the unmixing algorithm to complex data are both great challenges. In this article, we propose a novel unmixing method named spatial-spectral neighborhood preserving NMF (SSNPNMF) for incomplete and noisy HSI data. First, a spatial-spectral kernel regularizer is introduced to preprocess the HSI, which can reduce noise and complete missing elements. Second, a distance metric SSD based on spatial-spectral information is designed to select similar pixels in the image. Subsequently, the spatial-spectral relationship of the selected first k similar pixels is used to reconstruct the image and obtain the reconstruction matrix. Finally, the reconstruction matrix is used to constrain the abundances and improve the unmixing performance. Experimental results on synthetic data and Cuprite data indicate that SSNPNMF has a more effective unmixing performance compared with the state-of-the-art methods.

关键词Image reconstruction Hyperspectral imaging Noise measurement Gaussian noise Interference Stability analysis Sensors Hyperspectral unmixing (HU) image reconstruction nonnegative matrix factorization (NMF) spatial-spectral information
DOI10.1109/TGRS.2021.3101504
收录类别SCI ; EI
语种英语
WOS记录号WOS:000732810700001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
EI入藏号20220711631676
引用统计
被引频次:11[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.opt.ac.cn/handle/181661/95608
专题光谱成像技术研究室
通讯作者Yuan, Yuan
作者单位1.Northwestern Polytech Univ, Sch Artificial Intelligence Opt & Elect iOPEN
2.Chinese Acad Sci, Xian Inst Opt & Precis Mech
推荐引用方式
GB/T 7714
Dong, Le,Lu, Xiaoqiang,Liu, Ganchao,et al. A Novel NMF Guided for Hyperspectral Unmixing From Incomplete and Noisy Data[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2022,60.
APA Dong, Le,Lu, Xiaoqiang,Liu, Ganchao,&Yuan, Yuan.(2022).A Novel NMF Guided for Hyperspectral Unmixing From Incomplete and Noisy Data.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,60.
MLA Dong, Le,et al."A Novel NMF Guided for Hyperspectral Unmixing From Incomplete and Noisy Data".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 60(2022).
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
A Novel NMF Guided f(9737KB)期刊论文出版稿限制开放CC BY-NC-SA请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Dong, Le]的文章
[Lu, Xiaoqiang]的文章
[Liu, Ganchao]的文章
百度学术
百度学术中相似的文章
[Dong, Le]的文章
[Lu, Xiaoqiang]的文章
[Liu, Ganchao]的文章
必应学术
必应学术中相似的文章
[Dong, Le]的文章
[Lu, Xiaoqiang]的文章
[Liu, Ganchao]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。