训练样本数目选择对面向对象影像分类方法精度的影响

薄树奎; 丁  琳

doi:10.11834/jig.20100708

遥感图像处理 | 浏览量 : 0 下载量: 214 CSCD: 0

PDF
导出
分享
收藏
专辑

训练样本数目选择对面向对象影像分类方法精度的影响
The Effect of the Size of Training Sample on Classification Accuracy in Object-oriented Image Analysis
2010年15卷第7期页码：1106
网络出版：2010-07-23，

纸质出版：2010
DOI： 10.11834/jig.20100708
稿件说明：

移动端阅览

薄树奎, 丁琳. 训练样本数目选择对面向对象影像分类方法精度的影响[J]. 中国图象图形学报, 2010,15(7):1106. DOI： 10.11834/jig.20100708.

BO Shukui, DING Lin. The Effect of the Size of Training Sample on Classification Accuracy in Object-oriented Image Analysis[J]. Journal of Image and Graphics, 2010, 15(7): 1106. DOI： 10.11834/jig.20100708.

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。

Abstract

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.