植被高光谱遥感分类中训练样本的选择方法  

THE METHODS FOR SELECTING TRAINING SAMPLES IN VEGETATION CLASSIFICATION BASED ON HYPERSPECTRAL REMOTE SENSING

作　　者：陶秋香[1] 张连蓬[1] 李红梅[1] 

机构地区：[1]山东科技大学地球信息科学与工程学院,青岛266510

出　　处：《国土资源遥感》2005年第2期33-35,共3页Remote Sensing for Land & Resources

摘　　要：针对植被高光谱遥感分类过程中参考光谱训练样本的选择问题,研究分类过程中常用训练样本的选择方法,并在此基础上提出2种新的训练样本选择(纯化)方法,然后结合具体的OMIS-I高光谱遥感数据,验证方法的有效性。For the selection of training samples in vegetation classification based on hyperspectral remote sensing, this paper investigates and analyzes the methods for selection of training samples in common use, presents two new selection (purification) methods for training samples, and then testifies the validity of these methods which are combined with specific OMIS-I hyperspectral remote sensing data.

关 键 词：植被高光谱遥感分类 训练样本选择 训练样本纯化 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]