喀斯特石漠化地区遥感影像的决策树分类——以贵州省黔南州长顺县凯佐乡为例

Remote Sensing Image Classification Based on Decision Tree in Karst Rocky Desertification Areas—A Case Study of Kaizuo Township,Changshun County,Qiannan Prefecture,Guizhou Province

喀斯特石漠化是在自然和人为因素相互作用下土地退化的现象。石漠化地区的遥感影像分类以往采用的是监督分类和非监督分类,但它们单纯地利用像元的亮度特征,分类精度低,往往不能满足实际的应用需要。决策树分类是一种新的遥感影像分类技术。以凯佐乡为研究对象,使用了ASTER影像数据、DEM和岩性数据,通过提取归一化植被指数、比值植被指数、地形坡度等数据建立分类规则,构建决策树。在ENVI软件支持下,获得了研究区的决策树分类影像。通过计算影像分类精度和Kappa系数。得到了以下结论:运用决策树分类法对石漠化地区遥感影像进行分类,可取得较理想的分类效果;实现了石漠化信息的自动化提取;若采用的遥感影像波段更多,DEM分辨率更高并减少数据处理中的误差将能够进一步提高分类精度。

Karst rocky desertification is a phenomenon of land degradation as a result of affection by the interaction of natural and human factors.In the past,in the rocky desertification areas,supervised classification and unsupervised classification are often used to classify the remote sensing image.But they only use pixel brightness characteristics to classify it.So classification accuracy is low and can not meet the nccds of practical application.Decision tree classification is a new technology for remote sensing image classification.In this study,selecting the rocky desertification areas Kaizuo Township as a case study,using the ASTER image data,DEM and lithology data,classification rules were established to build decision trees by extracting the normalized difference vegetation index,ratio vegetation index,terrain slope and other data.With the ENVI software support,the classification images were obtained.By calculating the classification accuracy and Kappa coefficient,it was found that better classification results can be obtained,desertification information can be extracted automatically and if more remote sensing image bands used,higher resolution DEM employed and less errors data reduced during processing,classification accuracy can be improved further.