›› 2012, Vol. 25 ›› Issue (10): 23-.

• 论文 • 上一篇    下一篇

基于模糊聚类的SAR图像变化检测

贾彩杰   

  1. (西安电子科技大学 理学院,陕西 西安 710071)
  • 出版日期:2012-10-15 发布日期:2012-11-29
  • 作者简介:贾彩杰(1987—),女,硕士研究生。研究方向:目标优化图像处理。

Change Detection of SAR Images Based on Fuzzy Clustering

 JIA Cai-Jie   

  1. (School of Science,Xidian University,Xi'an 710071,China)
  • Online:2012-10-15 Published:2012-11-29

摘要:

利用两种模糊聚类算法即模糊C均值聚类(FCM)和Gustafson Kessel聚类(GKC),对SAR图像进行变化检测。差异图是根据不同时相图像的灰度值得到的,为了验证算法的有效性,实验选用两个不同地区的多时相图像,实验结果比较现存的马尔科夫随机场(MRF)和神经网络算法,不但耗用时间短,而且无需变化类和未变化类像素的任何先验分布信息。

关键词: 模糊C均值聚类, Gustafon Kessel聚类, SAR图像, 变化检测

Abstract:

This paper proposes two fuzzy clustering algorithms,namely Fuzzy C-Means(FCM) and Gustafson Kessel Clustering(GKC),which have been used to detect changes in SAR images.The Difference Images(DI) are obtained by the gray levels of multitemporal images.To show the effectiveness of the proposed algorithms,The multitemporal images of two difference regions are chosen.Results are compared with those of existing Markov Random Field(MRF) and neural network based algorithms.The proposed technique consumes less time and does not need any priori knowledge of the distribution of the changed and unchanged pixels.

Key words: fuzzy c-means;Gustafon Kessel clustering;SAR images;change detection

中图分类号: 

  • TP391.41