基于决策树分层分类法的粉煤灰堆场信息提取研究

Research on Using the Decision Tree Hierarchical Classification Method to Extract Fly Ash Information

粉煤灰污染环境,危害人类健康。应用遥感方法快速、实时、准确地识别粉煤灰堆场信息,对保护环境和人类健康具有重要意义。通过分析包头市辖区内典型地物的光谱信息,基于Landsat 5TM影像数据,采用决策树分层分类法对研究区内的粉煤灰堆场进行提取实验。首先,分析研究区内典型地物的光谱特征,对不同地物之间的关系进行比较。其次,建立决策树,利用土壤调节植被指数(SA-VI)、改进归一化差异水体指数(MNDWI)、归一化建筑指数(NDBI)以及光谱阈值法对图像进行了分类。最后利用形状特征和空间位置特征等对分类图像进行后处理,分类精度达到70.7%。实验结果表明:该方法适合粉煤灰堆场信息的自动提取,结合目视解译能够达到较高的识别精度。

Fly ash not only pollutes environment, but also endangers human health. It is of great significance to the protection of the environment and human health that distinguish fly ash rapidly, real-timely＇ accu rately based on remote sensing. The paper chooses Landsat 5 TM image as the source data and analysed the spectral information of the typical surface features in Baotou City. Then the study adopts the decision tree classification to extract fly ash in the study area. Firstly, analyzed the spectral characteristics of the typical objects and compared the relationship between them in the study area. Secondly, classified the image re spectively through established the decision tree, used Soil-adjusted Vegetation Index（SAVI）, Modified Nor malized Difference Water Index（MNDWI）, Normalized Difference Built-up Index（NDBI） and Spectrum Threshold Method. Ultimately,conducted post-process for the result of classification by shape feature and space feature. The total classification accuracy was up to 70.7~. The experimental results show that the method is suitable for the automatic extraction of fly ash information, can achieve high accuracy combined with the visual interpretation.