基于决策树的蓬莱市土地覆盖信息提取

Extraction of Land Covering Information Based on Decison Tree in Penglai City

摘要:

以蓬莱市为研究区，对TM影像经过预处理后，进行典型地物的光谱分析。在此基础上，运用决策树分类法，选取影像的光谱特征值、NDWI值、NDVI值、K[CD*2]T变换信息和DEM值等数据作为测试变量，选择适当阈值设定判别规则，建立决策树模型进行土地利用覆盖信息提取并做出精度评价。将其提取精度与监督分类结果精度进行比较，结果表明其分类精度有很大提高，尤其在研究区是丘陵地形的情况下，DEM数据的使用使林地、果园的可分性大大加强。

Abstract:

In this paper, taking Penglai as a study area, after the TM images of this area are preprocessed, spectrum analysis of typical surface features are carried out. On these basis, by using decision tree classification , selecting spectral characteristics, ND