节点文献

基于图论分割的多光谱图像非监督分类方法

Unsupervised classification approach based on graph-segment for multispectral remote sensing images

  • 推荐 CAJ下载
  • PDF下载
  • 不支持迅雷等下载工具,请取消加速工具后下载。

【作者】 刘娜娜李景文李宁

【Author】 Liu Nana Li Jingwen(School of Electronics and Information Engineering,Beijing University of Aeronautics and Astronautics,Beijing 100191,China)Li Ning(State Key Laboratory of Software Development Environment,Beijing University of Aeronautics and Astronautics,Beijing 100191,China)

【机构】 北京航空航天大学电子信息工程学院北京航空航天大学软件开发环境国家重点实验室

【摘要】 针对传统基于像素的多光谱遥感图像分类方法存在的"麻点"现象、采样成本高等问题,提出了一种基于图论分割的非监督分类方法,首先采用基于图论的分割算法,按局部邻近相似像素点分割成若干子区域,再以分割后子区域为基本单元,整体进行模糊C均值聚类,最终实现对多光谱图像的非监督分类.实验证明,该方法结合了局部邻近像素点的相互关系以及相似区域的整体特征,有效解决了麻点问题,具有较高的分类精度和算法效率,降低了采样成本.

【Abstract】 To solving the noisy points and high cost problems of pixel-based multispectral image classification,a hybrid unsupervised approach with graph-based segment and fuzzy c-means clustering was presented.First,based on the relationships among neighboring pixels,image was segmented into groups of sub-regions using the graph-based algorithm.Then according to the global feature vector of sub-region,the fuzzy c-means classifier was used to obtain the classification map.Experiments turn out that the proposed approach,which considers both relationships of neighboring pixels and global feature of sub-region,can achieve better accuracy and efficiency by comparing the result with pixel-based fuzzy c-means classification.

  • 【文献出处】 北京航空航天大学学报 ,Journal of Beijing University of Aeronautics and Astronautics , 编辑部邮箱 ,2009年05期
  • 【分类号】TP751
  • 【被引频次】11
  • 【下载频次】528
节点文献中: 

本文链接的文献网络图示:

本文的引文网络