基于CBERS-1图像的干旱半干旱区土地利用分类  

Landuse Classification in Arid and Semi-Arid Areas Using CBERS-1 Imagery

作　　者：刘爱霞[1] 刘正军[1] 王长耀[1] 牛铮[1] 

机构地区：[1]中国科学院遥感应用研究所遥感信息科学重点实验室,北京100101

出　　处：《中国科学院研究生院学报》2003年第3期334-340,共7页Journal of the Graduate School of the Chinese Academy of Sciences

基　　金：国家科技攻关计划项目(2 0 0 1DFBA0 0 0 5);中国科学院知识创新工程重大项目--中国陆地和近海生态系统碳收支研究(KZCX1 SW 0 1)资助

摘　　要：以中巴资源卫星CBERS 1图像数据为信息源,分别采用最大似然法、BP神经网络和Fuzzy ARTMAP神经网络 3种分类器,以位于干旱区的中国新疆石河子地区为例,进行了土地利用计算机自动分类。结果认为,3种方法中以Fuzzy ARTMAP神经网络法分类精度最高,分别比最大似然法和BP神经网络法提高了 1 0.69%和 6.84%。同时也证实了CBERSDiscussed and analyzed results of different classification algorithms for land use classification in arid and semiarid areas using CBERS 1 image, Which in case of our study is Shihezi Municipality, Xinjiang Province. Three types of classifiers are included in our experiment, including the Maximum Likelihood classifier, BP neural network classifier and Fuzzy ARTMAP neural network classifier. The classification results showed that the classification accuracy of Fuzzy ARTMAP was the best among three classifiers, increased by 10.69% and 6.84% than Maximum likelihood and BP neural network, respectively. Meanwhile, the result also confirmed the practicability of CBERS 1 image in land use survey.

关 键 词：CBERS-1图像 BP神经网络 Fuzzy-ARTMAP神经网络 土地利用分类 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置] X43[自动化与计算机技术—控制科学与工程]