浅谈基于特征构造的多光谱影像跨尺度分类研究方法

Discussion on Superficial Scale-Span Classification Approach for Multispectral Images Based on the Feature Construction

针对遥感多光谱影像处理,提出一种立足于多尺度像斑模型,应用数据挖掘中的特征构造来实现跨尺度特征构造的方法,将最佳尺度选择问题隐含在特征构造中,而不直接进行最佳尺度选择。从而在区分地物方面更加准确,分类精度更高。

In this paper,the method uses the feature construction of the data mining to fulfill the construction of scale-span features,and the best scale choice is implicit in the new constructive features,rather than directly carrying on the best scale choice.Thus it is more accurate in the aspect of distinguishing terrain feature.And the classified precision is higher.