CBERS-02星CCD数据土地利用分类方法研究--以江苏省宜兴地区为例  

Research on Land-use Classification Method Based on CBERS-02 Satellite Image

作　　者：申克建[1] 周伟[1] 袁春[1] 袁涛[1] 董国栋[1] 刘顺喜[2] 周连芳[2] 

机构地区：[1]中国地质大学土地科学技术学院,北京100083 [2]中国土地勘测规划院,北京100035

出　　处：《遥感信息》2009年第2期71-75,共5页Remote Sensing Information

基　　金：国土资源部项目“中巴资源卫星土地宏观监测应用研究”

摘　　要：以江苏省宜兴地区为试验区,首先进行了CBERS-02星CCD数据的图像预处理,然后利用ERDASI-MAGINE和Definiens7.0等软件,采用非监督分类、监督分类、混合监督分类、面向对象四种分类方法进行了土地利用分类,并将影像分类结果进行了精度评价分析。结果表明:在一级地类的提取中,面向对象的最邻近分类器的分类精度最低,混合监督分类的精度最高;在二级地类的提取中,面向对象的特征阈值法得到的分类结果较好,能够轻松提取传统分类方法难于提取的地类。Taking Yixing City of Jiangsu Province as a test field and based on multi-spectral remote sensing image data of CBERS-02 CCD, this paper firstly made a series of image pre-processing. Then, by using ERDAS IMAGINE and Definiens7. 0, the land use categories were extracted by unsupervised classification, supervised classification, integration of supervised classification and visual interpretation, object-oriented approach. Finally, this paper made a comparison of the four classification precisions. Experiment indicated that., among the extraction of prime types, the lowest classification precision is Nearest Neighbor Classifier of object-oriented approach, and the highest classification precision is integration of supervised classification and visual interpretation. As the extraction of secondary type is concerned, the methods based on Features of object-oriented approach have a relatively satisfactory result, as they could easily extract some secondary types which are hardly to be extracted by traditional methods.

关 键 词：中巴资源卫星 土地利用 分类精度 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]