唐山市区土地利用的Landsat 8影像分层分类

针对土地利用遥感分类方法多样、分类精度高低不一等问题,该文以土地利用变化明显的唐山市路南区、路北区为研究区域,并以中分遥感影像Landsat 8OLI为信息源,在对地类样本进行可分离性分析的基础上,建立研究区土地利用分层分类体系。通过监督分类实验,选择分类效果最好、分类精度最高的最大似然分类器进行地类初分;通过绘制归一化植被指数(NDVI)、归一化建筑指数(NDBI)、两指数差值(NDVI-NDBI)的曲线及地类光谱特征曲线,建立决策树分类规则,进行地类再分。该方法可以较好地完成多种土地利用二级地类的划分,有助于提高中分影像土地利用分类效率。

Land use hierarchical classification based on Landsat 8 image in Tangshan city

According to the problems that the methods in land use remote sensing classification are variousand the classification results are different,this paper took the Lunan and Lubei districts of Tangshan city as an example and set up the land use hierarchical classification system using Landsat 8 remote sensing image based on the analysis of the separability of land type sample.Through the supervised classification,the maximum likelihood method was chosen for initial classification;then,the curve of normalized difference vegetation index (NDVI),normalized difference built-up index (NDBI),NDVI NDBI were drew and the classification rules of decision tree was built for secondary classification.Finally,the land use hierarchical classification was completed.The proposed method could well classify the second land use type,which improved the efficiency of land use classification in mid and sub regional images.