面向对象的高分辨率卫星影像土地分类

Object-oriented Land-use Information Extraction from Satellite Imagery

本文采用面向对象的方法对高分辨率卫星影像进行土地分类信息提取。首先利用最近邻分类法对多尺度分割后形成的影像对象块粗分类。随后根据各地类的影像特征构建知识库,优化错分类的地类信息。试验表明,面向对象的高分辨率影像土地分类能充分利用影像信息,提高了信息提取的精度。

This paper proposes an objected-oriented method to extract land-use from high-resolution satellite image. Firstly, the nearest neighbor classification method is used to obtain rough classification result though judgment of image objects. These image objects come from multiresolution segmentation to raw image. Then, the knowledge base is constructed according to the image features of different classes. Lastly, land-use information is optimized using knowledgebase. The experiment result show that object-oriented land-use information extraction could use image information completely and obtain better effect.