为了从不同时相的遥感影像数据中自动提取变化信息且保证其效率,本文结合面向对象分析技术,提出了一种基于决策树变化信息自动提取的新方法。该方法利用影像的特征指数及形状特征、光谱特征、纹理特征等作为特征集,将其作为知识库应用到决策树控制模型中,进而利用该模型实现自动分类。对所得到的分类后影像对象,组织分析其综合属性并作为决策规则再次分类,通过"双重分类"的方式实现面向对象的遥感影像变化信息自动提取。该方法为遥感影像变化信息自动提取提供了新的思路。 更多还原
【Abstract】 In order to extract change information automatically from the different time remote sensing images and to ensure the efficiency,a new automatic extraction method which is combined with the object-oriented image analysis technology based on the decision tree is presented in this paper.This method uses the feature index and shape,spectral,texture of the image as a feature set to establish the decision tree model for automatic classification.Organize and analyze the synthesized attributes of image ... 更多还原