Study on Extracting Information about Settlements Distribution in Western Jilin Province Based on Decision Tree Model  

基于决策树模型的吉林西部居民地分布信息提取(英文)

作　　者：连懿[1] 陈圣波[1] 王亚楠[1] 逄超 

机构地区：[1]吉林大学地球探测科学与技术学院,吉林长春130026

出　　处：《Journal of Landscape Research》2010年第2期92-95,共4页景观研究（英文版）

基　　金：Supported by Financial Support of China Geological Survey(1212010916048);the Fundamental Research Funds for the Central Universities(200903046)~~

摘　　要：With western Jilin Province as the study region, spectral characteristics and texture features of remote sensing images were taken as the classification basis to construct a Decision Tree Model and extract information about settlements in western Jilin Province, and the manually-extracted information about settlements in western Jilin Province was evaluated by confusion matrix. The results showed that Decision Tree Model was convenient for extracting settlements information by integrating spectral and texture features, and the accuracy of such a method was higher than that of the traditional Maximum Liklihood Method, in addition, calculation methods of extracting settlements information by this mean were concluded.以吉林西部为研究区,对遥感图像进行几何校正和多波段融合镶嵌处理,将图像自西向东依次分为A、B、C、D4个区域,以遥感影像的光谱特征和纹理特征作为分类依据,建立决策树模型,即建立典型地物均值表和光谱图以及居民地决策树(包括河滩地、农田与林地、水体、盐碱地),提取居民地信息,并选用手动提取的吉林西部居民地信息,利用混淆矩阵对其进行精度评价。结果表明,决策树易于综合光谱和纹理特征进行居民地信息提取,通过对比发现,利用决策树方法提取的居民地的精度明显高于传统的最大似然法,即居民地用户精度为81.97%,而生产精度为84.73%,相对于最大似然法分别提高了26.48%、14.15%。并总结出了利用该方法提取居民地信息的算法。

关 键 词：SETTLEMENTS TM Western Jilin Province Spectral characteristics Texture features Decision Tree Confusion matrix 

分 类 号：K928.5[历史地理—人文地理学] TP751[自动化与计算机技术—检测技术与自动化装置]