期刊论文

中文

中国图象图形学报

1006-8961

2005

10

12

1504-1510

10.3969/j.issn.1006-8961.2005.12.004

国家自然科学基金项目（30471391）； 湖南省***基金项目（02JJBY005）； 湖南省教育厅青年基金项目（04B059）；

本校为第一机构

信息识别是目前高分辨率遥感应用中的最大障碍.以株洲市QuickBird图像为研究对象,将研究区分为道路、水、林地、农用地、裸露地和居民点6种地类,分别进行目视判读、计算机监督分类和非监督分类,其精度分别为98.2%、72.64%和60.71%.同时,还对研究区内的QuickBird、ETM+和TM图像进行计算机监督和非监督分类对比,结果表明无论是监督分类还是非监督分类,QuickBird图像的分类精度均低于ETM+和TM图像,这说明空间分辨率的提高对传统的计算机分类结果没有改善,传统的基于像元的分类技术在应用于QuickBird图像时表现出严重的缺陷.因此,本文回避了像元灰度统计法,采用先将图像分割,将以像元为基础的QuickB...

The information identification is the most difficult in the application of high-resolution remote sensing images. This paper focused on the method of QuickBird image＇s information extraction. Six kinds of land cover types： road, water, forest, agriculture, nuke and residence in the study area, Zhuzhou, Hunan, were identified by visual interpretation, supervised classification and non-supervised classification respectively, and the accuracy is 98.2% , 72.64% and 60.71% correspondingly. At the same time, pre-processed images of QuickBird, ETM ＋...