高光谱图像端元提取算法研究进展与比较

李二森; 朱述龙; 周晓明; 余文杰

doi:10.11834/jrs.20110156

综述 | 浏览量 : 0 下载量: 2480 CSCD: 17

PDF
导出
分享
收藏
专辑

高光谱图像端元提取算法研究进展与比较
The development and comparison of endmember extraction algorithms using hyperspectral imagery
2011年15卷第4期页码：659-679
纸质出版：2011
DOI： 10.11834/jrs.20110156
稿件说明：

移动端阅览

[1]李二森,朱述龙,周晓明,余文杰.高光谱图像端元提取算法研究进展与比较[J].遥感学报,2011,15(04):659-679. DOI： 10.11834/jrs.20110156.

The development and comparison of endmember extraction algorithms using hyperspectral imagery[J]. Journal of Remote Sensing, 2011, 15(4): 659-679. DOI： 10.11834/jrs.20110156.

摘要

高光谱图像中混合像元的存在不仅影响了基于遥感影像的地物识别和分类精度

而且已经成为遥感科学向定量化方向发展的主要障碍。本文分析和研究了现有的典型端元提取算法

在此基础上

对这些算法进行归纳总结

从是否假定纯像元存在角度将其分为两类:端元识别算法和端元生成算法

并就两种分类方法选取了具有代表性的6种典型端元提取算法:N-FINDR、VCA、SGA、OSP、ICE和MVC-NMF算法进行分析和实验。通过对这6种方法的实验比较

得出两种端元提取分类方法的优点与不足

并对今后的研究工作提出展望。

Abstract

The mixels in the hypersepectral images not only influence the accuracy of target detection and classification

but also greatly hinder the development of quantitative remote sensing. The typical endmember extraction algorithms now available are analyzed and summarized. These algorithms can be classified into two types based on the hypothesis of the existence of the pure pixels: endmember identiflcation algorithm and endmember generation algorithm. Six endmember extraction algorithms

including N-FINDR

VCA

SGA

OSP

ICE and MVC-NMF

are introduced and compared using experimental data

which further show their advantages and disadvantages. With results of various methods

the future perspective is proposed for further study.