首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于信息融合的遥感分类与回归分析研究
引用本文:白文路,赵巍,崔淑梅,唐降龙.基于信息融合的遥感分类与回归分析研究[J].燕山大学学报,2010,34(2):138-142.
作者姓名:白文路  赵巍  崔淑梅  唐降龙
作者单位:1. 哈尔滨工业大学计算机科学与技术学院,黑龙江哈尔滨,150001
2. 哈尔滨工业大学电气工程及自动化,学院,黑龙江哈尔滨,150001
摘    要:本文提出了组合纹理和光谱信息的遥感图像解译技术,将其运用于陆地水体的二元分类,目的是通过组合两种分析方法的优点,得到更好的解译结果。利用灰度共生矩阵来进行纹理分析,同时,红光和红外光谱分析的使用能够改善陆地和水体的分类边界。纹理分析和光谱特征的融合改进了两类标记的精确度。在此基础上,本文针对多光谱数据的特点提出了灰度级差联合概率矩阵(GLDAP),利用提取的特征对多光谱高度数据进行了回归分析。

关 键 词:多光谱遥感图像  纹理特征  光谱特征  

Classification and regression analysis of remote sensing images by information fusion
BAI Wen-lu ,ZHAO Wei ,CUI Shu-mei ,TANG Xiang-long.Classification and regression analysis of remote sensing images by information fusion[J].Journal of Yanshan University,2010,34(2):138-142.
Authors:BAI Wen-lu  ZHAO Wei  CUI Shu-mei  TANG Xiang-long
Institution:1. School of Computer Science and Technology;Harbin Institute of Technology;Harbin;Heilongjiang 150001;China;2. School of Electrical Engineering and Automation;China
Abstract:A remote sensing interpretation technique combined texture and spectral information, for land/water classification, is given in this paper,in order to get better results taking advantage of both analyses.By using texture based on grey level co-occurrence matrix (GLCM) and red/infrared spectral information, a refined boundary of land/water was obtained, which improved the accuracy of the land type labeling. On this basis, a gray level difference associated possibility matrix (GLDAP), in view of the character...
Keywords:multi-spectral remote sensing image  texture feature  spectral feature  
本文献已被 CNKI 维普 万方数据 等数据库收录!
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