A method of endmember extraction in hyperspectral image based on landmark isometric mapping

Q4 Physics and Astronomy
唐晓燕 Tang Xiaoyan, 高. G. Kun, 刘. L. Ying, 倪国强 Ni Guoqiang
{"title":"A method of endmember extraction in hyperspectral image based on landmark isometric mapping","authors":"唐晓燕 Tang Xiaoyan, 高. G. Kun, 刘. L. Ying, 倪国强 Ni Guoqiang","doi":"10.3788/GXJS20144005.0402","DOIUrl":null,"url":null,"abstract":"A fast endmember extraction method based on landmark point selection is presented to overcome the high complexity and memory usage of the classical Isomap-NFINDR algorithm.The proposed method uses the maximin distance method to initial the kcluster centers,and carries out clustering segmentation using spectral angle instead of Euclidean distance.According to the spatial characteristics of the image,Nlandmark points which are near to cluster center are selected from the remaining points after removing the boundary points.Experiments with real images reveal that the algorithm proposed has the similar accuracy with the original algorithm and its operational efficiency is improved by 60 times.","PeriodicalId":35591,"journal":{"name":"光学技术","volume":"40 1","pages":"402-405"},"PeriodicalIF":0.0000,"publicationDate":"2014-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"光学技术","FirstCategoryId":"1089","ListUrlMain":"https://doi.org/10.3788/GXJS20144005.0402","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Physics and Astronomy","Score":null,"Total":0}
引用次数: 0

Abstract

A fast endmember extraction method based on landmark point selection is presented to overcome the high complexity and memory usage of the classical Isomap-NFINDR algorithm.The proposed method uses the maximin distance method to initial the kcluster centers,and carries out clustering segmentation using spectral angle instead of Euclidean distance.According to the spatial characteristics of the image,Nlandmark points which are near to cluster center are selected from the remaining points after removing the boundary points.Experiments with real images reveal that the algorithm proposed has the similar accuracy with the original algorithm and its operational efficiency is improved by 60 times.
基于地标等距映射的高光谱图像端元提取方法
针对经典Isomap-NFINDR算法的高复杂度和内存占用问题,提出了一种基于地标点选择的快速端元提取方法。该方法采用最大距离法初始化聚类中心,利用谱角代替欧氏距离进行聚类分割。根据图像的空间特征,去除边界点后,从剩余点中选取离聚类中心较近的n个landmark点。实际图像实验表明,该算法具有与原算法相近的精度,运算效率提高了60倍。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
光学技术
光学技术 Physics and Astronomy-Atomic and Molecular Physics, and Optics
CiteScore
0.60
自引率
0.00%
发文量
6699
期刊介绍: The predecessor of Optical Technology was Optical Technology, which was founded in 1975. At that time, the Fifth Ministry of Machine Building entrusted the School of Optoelectronics of Beijing Institute of Technology to publish the journal, and it was officially approved by the State Administration of Press, Publication, Radio, Film and Television for external distribution. From 1975 to 1979, the magazine was named Optical Technology, a quarterly with 4 issues per year; from 1980 to the present, the magazine is named Optical Technology, a bimonthly with 6 issues per year, published on the 20th of odd months. The publication policy is: to serve the national economic construction, implement the development of the national economy, serve production and scientific research, and implement the publication policy of "letting a hundred flowers bloom and a hundred schools of thought contend".
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信