通过添加树平衡系数、设定节点不纯度和区分样本类型,对现有的随机决策树群算法进行了改进,提出了改进的随机决策树群算法。以广东省龙门县土地覆盖的ALOS遥感影像为研究对象,利用改进的随机决策树群算法对研究对象进行遥感监督分类,并将研究结果同传统的最大似然分类方法的结果进行对比,发现分类总体精度从81.46%提高至92.45%,Kappa系数达0.9091。改进的随机决策树群算法考虑了极不均衡决策树、节点不纯度和训练样本区分对随机决策过程运行效率的影响,可有效提高遥感分类效率和分类精度。 更多还原
【Abstract】 An improved Random Decision Trees algorithm with application to land cover remote sensing classification was proposed in this paper.Firstly,an improved Random Decision Trees algorithm was presented by adding tree balance factor,setting node impurity and distinguishing sample types.Secondly,by taking the ALOS images of Longmen City of Guangdong Province in China as study area,the remote sensing classification was conducted using the improved Random Decision Trees algorithm.Finally,a comparison st...