基于案例推理的植被提取方法研究

Research on the Method of Vegetation Extraction Based on Case-Based Reasoning

针对基于案例推理在植被提取方面的研究较少的现状,为实现高分辨率遥感影像植被高精度提取,重点研究了基于案例推理的植被提取方法。详细阐述了基于案例推理系统的构成,重点论述了案例表示中的特征选择和案例检索过程中的相似度算法及特征属性权重优化方法。根据理论研究,成功开发了植被提取案例推理系统,并基于窗口匹配方法进行改进,植被提取精度可达到91%。结果表明:基于案例推理的植被提取方法可实现高分辨率遥感影像植被高精度提取。

In view of the current situation that there is less research of case-based reasoning in vegetation extraction,in order to achieve high-precision vegetation extraction from high-resolution remote sensing images,this paper focuses on the research of vegetation extraction method based on case-based reasoning.This paper describes the structure of case-based reasoning system in detail,and focuses on feature selection in case representation,similarity algorithms and feature attribute weight optimization methods in the process of case retrieval.Based on the above theoretical research,the case-based reasoning system for vegetation extraction was successfully developed and improved based on the window matching method.The accuracy of vegetation extraction reached 91%.The results show that the vegetation extraction method based on case-based reasoning can achieve high-precision vegetation extraction from high-resolution remote sensing images.