光谱特征分析是森林类型识别的前提。使用ALOS遥感数据,通过单波段、多波段统计方法分析波段数据特征,获得对影像的整体认识;运用归一化植被指数、主成分分析以及最佳指数法,计算不同森林类型的光谱特征;通过与最大似然法对比,结合实地调查数据,构造出理想的决策树算法,研究森林类型的识别问题。结果表明:ALOS数据4个波段中,波段4独立性较强,在遥感信息提取中是必选波段;NDVI及主成分变换可显著增强地物区分度,为森林类型识别研究的波段组合提供参考;同最大似然法相比,决策树分类精度显著提高,Kappa系数达0.878 7;该算法可降低混合分类现象,提高森林类型识别精度。 更多还原
【Abstract】 Spectral feature analysis is the first premise of forest type recognition.Band characteristics were analyzed to thoroughly understand ALOS data by single-band and multi-band statistical methods,and spectral characteristics of different forest types were computed by adopting Normalized Difference Vegetation Index(NDVI),Principal Component Analysis(PCA) and Optimum Index Factor(OIF).The ideal decision tree classification algorithm was built to study the forest type recognition of Pingnan County in... 更多还原