首页 | 本学科首页   官方微博 | 高级检索  
     

遥感图像分类方法及研究进展
引用本文:陈姝,居为民. 遥感图像分类方法及研究进展[J]. 河北农业科学, 2009, 13(1): 143-146
作者姓名:陈姝  居为民
作者单位:南京大学国际地球系统科学研究所,江苏 南京,210093
摘    要:随着遥感技术的不断发展,仅仅依靠传统的计算机分类方法对遥感影像进行分类,有明显的不足之处。近年来出现了一些新方法,并且越来越广泛的被接受和应用。众多研究表明,将传统的计算机分类方法和新方法加以结合,可以有效减少错分、漏分的情况,使不易识别的地物能够被方便地提取出来,提高了图像分类的精度。

关 键 词:人工神经网络  决策树  特征融合  频谱

Classification Methods and Progress of Remote Sensing Image
CHEN Shu,JU Wei-min. Classification Methods and Progress of Remote Sensing Image[J]. Journal of Hebei Agricultural Sciences, 2009, 13(1): 143-146
Authors:CHEN Shu  JU Wei-min
Affiliation:International Institute of Earth System Science;Nanjing University;Nanjing 210093;China
Abstract:With the development of remote sensing technology,there were obvious shortcomings,when the remote sensing image was classified only rely on the traditional classification methods by computer.In recent years,some new methods appeared,which were more and more accepted and widely used.Many studies had shown that the traditional classification methods by computer were combined with new methods,which could effectively reduce wrong and omission,easily extract the ground features which were difficult to identify,a...
Keywords:Artificial neural networks  Decision tree  Fusion of multi-scale features  Frequency spectroscopy  
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