首页 | 本学科首页   官方微博 | 高级检索  
     

一种端元可变的混合像元分解方法
引用本文:丛浩,张良培,李平湘.一种端元可变的混合像元分解方法[J].中国图象图形学报,2006,11(8):1092-1096.
作者姓名:丛浩  张良培  李平湘
作者单位:武汉大学测绘遥感信息工程国家重点实验室,武汉430079
基金项目:国家自然科学基金;国家重点基础研究发展计划(973计划)
摘    要:混合像元线性分解是高光谱影像处理的常用方法,它使用相同的端元矩阵对像元进行分解,其结果是分解精度不高。为此提出了一种端元可变的混合像元分解方法,在确定端元矩阵时,首先考察混合像元与端元的光谱相似性,结合地物空间分布特点,实现了可变端元的混合像元分解。试验结果表明,该分解方法分解精度优于传统线性模型,符合实际情况。

关 键 词:端元可变  混合像元  遥感  影像分类
文章编号:1006-8961(2006)08-1092-05
收稿时间:2005-05-26
修稿时间:2005-05-262005-09-02

A Method of Selective Endmember for Pixel Unmixing
CONG Hao,ZHANG Liang-pei,LI Ping-xiang,CONG Hao,ZHANG Liang-pei,LI Ping-xiang and CONG Hao,ZHANG Liang-pei,LI Ping-xiang.A Method of Selective Endmember for Pixel Unmixing[J].Journal of Image and Graphics,2006,11(8):1092-1096.
Authors:CONG Hao  ZHANG Liang-pei  LI Ping-xiang  CONG Hao  ZHANG Liang-pei  LI Ping-xiang and CONG Hao  ZHANG Liang-pei  LI Ping-xiang
Affiliation:State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan 430079
Abstract:Linear pixel unmixing is a straightforward and efficient approach to the spectral decomposition of hyperspectral remotely sensed scenes,which involves only a single pixel with the same mixing proportions.In this paper we develop a method of selective endmembers for pixel unmixing.The proposed algorithm compares pixel spectral with endmember spectral and take the neighboring pixel into account when selecting the endmember matrix(EM).Experimental results show that the selective endmember algorithm achieves improvement over conventional linear algorithms.
Keywords:selective endmembers  mixed pixel  remote sensing  image classification
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《中国图象图形学报》浏览原始摘要信息
点击此处可从《中国图象图形学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号