Blind Hyperspectral Unmixing Based on Graph Total Variation Regularization

Jing Qin; Harlin Lee; Jocelyn T. ChiLucas DrumetzJocelyn ChanussotYifei LouAndrea L. Bertozzi

首页> 外文期刊>IEEE Transactions on Geoscience and Remote Sensing >Blind Hyperspectral Unmixing Based on Graph Total Variation Regularization

【24h】

Blind Hyperspectral Unmixing Based on Graph Total Variation Regularization

机译：Blind Hyperspectral Unmixing Based on Graph Total Variation Regularization

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相关主题

摘要

Remote sensing data from hyperspectral cameras suffer from limited spatial resolution, in which a single pixel of a hyperspectral image may contain information from several materials in the field of view. Blind hyperspectral image unmixing is the process of identifying the pure spectra of individual materials (i.e., endmembers) and their proportions (i.e., abundances) at each pixel. In this article, we propose a novel blind hyperspectral unmixing model based on the graph total variation (gTV) regularization, which can be solved efficiently by the alternating direction method of multipliers (ADMM). To further alleviate the computational cost, we apply the Nystr?m method to approximate a fully connected graph by a small subset of sampled points. Furthermore, we adopt the Merriman–Bence–Osher (MBO) scheme to solve the gTV-involved subproblem in ADMM by decomposing a gray-scale image into a bitwise form. A variety of numerical experiments on synthetic and real hyperspectral images are conducted, showcasing the potential of the proposed method in terms of identification accuracy and computational efficiency.

著录项

来源
《IEEE Transactions on Geoscience and Remote Sensing》 |2021年第4期|3338-3351|共14页
作者
Jing Qin; Harlin Lee; Jocelyn T. ChiLucas DrumetzJocelyn ChanussotYifei LouAndrea L. Bertozzi;
展开▼
作者单位

University of Kentucky, Lexington, KY, USA;

Carnegie Mellon University, Pittsburgh, PA, USA;

IMT Atlantique, LAb-STICC, Université Bretagne Loire (UBL), Brest, FranceGIPSA-Laboratory, CNRS, Grenoble Institute of Technology (Grenoble INP), Université Grenoble Alpes, Grenoble, FranceThe University of Texas at Dallas, Richardson, TX, USAUniversity of California at Los Angeles, Los Angeles, CA, USANorth Carolina State University, Raleigh, NC, USA;

展开▼
收录信息
原文格式 PDF
正文语种英语
中图分类地球物理学;遥感技术;
关键词
Hyperspectral imaging; TV; Laplace equations; Convex functions; Computational modeling; Computational efficiency;

Blind Hyperspectral Unmixing Based on Graph Total Variation Regularization

摘要

著录项

相关主题

期刊订阅