| 基于决策树的遥感影像分类方法研究 |
| |
| 引用本文： | 李爽,张二勋. 基于决策树的遥感影像分类方法研究[J]. 地域研究与开发, 2003, 22(1): 17-21 |
| |
| 作者姓名： | 李爽 张二勋 |
| |
| 作者单位： | 1. 河南大学环境与规划学院,河南,开封,475001;聊城师范学院地理系,山东,聊城,252059
2. 河南大学环境与规划学院,河南,开封,475001 |
| |
| 基金项目： | 河南省杰出青年科学基金资助项目 ( 0 0 0 3 ,992 0 ) |
| |
| 摘 要： | 基于决策树分类算法在遥感影像分类方面的深厚潜力。探讨了3种不同的决策树算法（UDT、MDT和HDT）。首先对决策树算法结构。算法理论进行了阐述：具体利用决策树算法进行遥感土地覆盖分类实验，并把获得的结果与传统统计分类法进行比较，研究表明，决策树分类法相对简单，明确，分类结构直观，有诸多优势。
|
| 关 键 词： | 决策树 遥感影像 最大似然分类法 土地覆盖 UDT MDT HDT |
| 文章编号： | 1003-2363(2003)01-0017-05 |
The Decision Tree Classification and Its Application in Land Cover |
| |
| LI Shuang ,,ZHANG Re-xun. The Decision Tree Classification and Its Application in Land Cover[J]. Areal Research and Development, 2003, 22(1): 17-21 |
| |
| Authors: | LI Shuang ZHANG Re-xun |
| |
| Affiliation: | LI Shuang 1,2,ZHANG Re-xun 1 |
| |
| Abstract: | Decision tree classification algorithms have significant potential for remote sensing data classification. In this research, three different types decision tree classification (UDT, MDT and HDT) are present. First, the paper discussed the algorithms structure and the algorithms theory of decision tree. Second, decision tree algorithms have been used to play land cover classification from remotely sensed data, and compare the result with conventional statistics classification. The results of this research showed that decision trees have several advantages for remote sensing applications by virtue of their relatively simple, explicit, and intuitive classification structure. |
| |
| Keywords: | decision tree classification remote sensing image maximum likelihood classification |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
