高分辨率影像的面向对象土地分类方法研究

Research on object-oriented land classification method based on high-resolution imagery

国土规划是城市发展建设的关键因素之一,文章基于eCognition平台采用基于样本的面向对象分类方法对研究区的高分二号遥感影像土地分类,并与传统的土地分类方法—监督分类进行分类结果对比评价,实验结果表明:相较于传统的监督分类方法,面向对象分类方法的分类效果更好,分类精度更高,可靠性更佳,并且能为国土规划建设提供更可靠的参考依据,从而使决策者做出更加合理的规划建设。

Land planning is one of the key factors of urban development and construction,based on eCognition platform,this paper adopts the sample-based object-oriented classification method to classify the land of Gaofen-2 remote sensing image in the study area,and compares and evaluates the classification results with the traditional land classification method-supervised classification,and the experimental results show that compared with the traditional supervised classification method,the objectoriented classification method has better classification effect,higher classification accuracy and better reliability,and can provide a more reliable reference basis for land planning and construction.So that decision-makers can make more reasonable planning and construction.