分层分类与监督分类相结合的遥感分类法研究  

A Study on A Classification Method of Remote Sensing Combined Stratified Classification with Supervised Classification

作　　者：刘礼[1] 于强[2] 

机构地区：[1]南京林业大学森林资源与环境学院,江苏南京210037 [2]昆明理工大学国土资源工程学院,云南昆明650000

出　　处：《林业调查规划》2007年第4期37-39,44,共4页Forest Inventory and Planning

基　　金：吉林省科技厅重点项目;中国科学院遥感信息科学重点实验室开放基金支持

摘　　要：遥感分类技术是获取土地利用/覆盖数据的主要方法。分层分类思想强调将分类过程逐级进行,每层选用不同的分类标准和方法;监督分类是基于传统统计分析的分类法,具有算法成熟,简便易行的特点。将2种方法相结合,建立起一个复合分类模型,并在SPOT影像上进行试验。试验证明:该方法能有效地提高分类精度,比单一使用监督分类法得到的结果精度提高了8.41%。The technology of remote sensing image classification is the main means of LUCC research. The stratified classification is a method based on the idea of division of layers step by step and different criteria and methods in each layer; while the supervised classification highlights traditional statistical and analytic approach, which is a mature algorithm, simple and convenient as well as easily being operated. Combining these two methods is to establish a compound classification model which is tested in SPOT im-age. The result shows that this method can effectively improve precision of classification. In detail, com-pared with supervised classification method, the result from compound method improves 8.41% of the precision.

关 键 词：分层分类 监督分类 遥感分类 决策树分类器 复合分类模型 遥感影像 

分 类 号：S771.8[农业科学—森林工程] G254.1[农业科学—林学]