基于决策树的Landsat 多光谱影像分类方法.pdf

文档介绍：26 3 26 3
第2011卷第6 期光电技术应用 Vol. ,2011No.
年月 ELECTRO-OPTIC TECHNOLOGY APPLICATION June,
·信号与信息处理·
基于决策树的Landsat多光谱影像分类方法
黄立贤,沈志学
(中国工程物理研究院流体物理研究所,四川绵阳 621900)
摘要:构建了一种结合光谱特征和纹理特征的多光谱影像决策树分类方法。以Landsat-7影像作为试验数据,通过分析
-
Landsat 7 影像的光谱特征值及 NDVI、NDWI 和 NDBI 特征值,确定各类地物的综合阈值,同时运用灰度共生矩阵对影像进行
-
纹理信息提取,得到对比度、熵、逆差矩和相关性等纹理特征图像。在此基础上,运用决策树分类法对 Landsat 7 影像进行分
类。结果表明,结合光谱特征和纹理特征的决策树分类方法,相比传统的最大似然法和决策树法,具有更高的分类精度。
关键词:多光谱影像;决策树分类;纹理特征;光谱特征
- - -
中图分类号:TP751;P237 文献标识码:A 文章编号:1673 1255(2011)03 0049 04
Classification Methods of Landsat Multi-spectral Images Based on Decision Tree
HUANG Li-xian SHEN Zhi-xue
,
621900
(Institute of Fluid Physics,China Academy of Engineering Physics,Mianyang ,China)
Abstract: A classification method of decision tree for multi-spectral images,bines the spectral
features with the texture features is presented. The Landsat-7 images are taken as the experiment data,the inte⁃
grated thresholds of the various ground objects are determined by analyzing characteristic values of the Land⁃
sat-7 images spectrum,NDVI,NDWI and NDBI. Meanwhile,the texture information of images including the
contrast,entropy,homogeneity and correlation are acquired by means of using Gray Level Co-occurrence Matri⁃
ces. On this basis the Landsat-7 images are classified by the decision tree classification method. The results indi⁃
cate that the accuracy