摘要
面向对象遥感影像分类中的样本选择与基于像素的方法有很大不同,基于统计学理论,研究了面向对象方法的样本数量选择问题。首先,针对面向对象方法的特点,对影像特征空间进行分析,结果表明面向对象方法中要求训练样本的数量可以显著地减少。然后,在遥感影像分类实验中,借助样本数量与波段数目的关系,验证了理论分析的结果。
As opposed to per-pixel classification, the selection of training samples is different in object-oriented method. Based on statistical theory, the number of training samples required in object-oriented classification is studied in this paper. First,feature space analysis of images is implemented in object-oriented classification, which shows that the number of training samples needed for object-oriented classification is much less than that in per-pixel classification. Then, an experiment of remote sensing image classification is carried out to verify the authenticity based on the relations between samples and bands.
出处
《中国图象图形学报》
CSCD
北大核心
2010年第7期1106-1111,共6页
Journal of Image and Graphics
基金
国家自然科学基金项目(40771140)
河南省科技攻关计划项目(092102210307)
河南省高等学校青年骨干教师资助计划
河南省科技厅基础与前沿技术研究计划(092300410043)
关键词
分类
面向对象
训练样本
遥感影像
classification, object-oriented, training samples, remote sensing image
