土地利用信息的多元分析提取  

Study on Extraction Method of Land Use Information

作　　者：党安荣[1] 何新东[1] 史慧珍[1] 桂丹[1] 

机构地区：[1]清华大学人居环境研究中心GIS实验室,北京100084

出　　处：《地球信息科学》2004年第2期63-66,共4页Geo-information Science

基　　金：北京市科学技术委员会科技项目(955410400);清华大学基础研究基金支持项目(Jc2000006)。

摘　　要：由遥感(RS)、地理信息系统(GIS)和全球定位系统(GPS)获取、处理、分析空间信息,已成为研究资源环境的重要技术手段。在土地利用信息提取中,我们先后应用了传统目视解译方法、人机交互解译方法、计算机自动分类方法、多源信息复合分析等方法。本文在分析现有各种方法优缺点的基础上,提出了“综合自动分类方法”,并以北京市密云县为例,对土地利用信息进行了提取。分析表明:综合自动分类方法在分类结果的客观性、科学性、实用性等方面,具有一定的优势。S technologies, which refer to Remote Sensing (RS), Geographic Information System (GIS), and Global Positioning System (GPS), are very important techniques in resources investigation and environmental protection because of the unique characteristics in information acquiring, processing, and analyzing. For extraction of land use information, four main methods have been used until now, such as traditional manual interpreting method,humancomputer interactive interpreting method,computer aided auto-classification method, and multi-information complex interpreting method. After analyzing the advantages and disadvantages of each of the above method, a new kind of method called integrated auto-classification method is put forward based on mature auto-classification methods. Taking Miyun County, Beijing as a case region, the land use information was extracted by means of the new method-integrated auto-classification method supported by 3S technologies. A series of contrast analysis have been done between the new method and traditional method. Result of this study can be deduced that the new method has some advantages in objectivity, scientificness, and practicability.

关 键 词：土地利用 信息提取 综合自动分类方法 

分 类 号：P228.4[天文地球—大地测量学与测量工程]