• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2012, Vol. 34 ›› Issue (10): 83-87.

• 论文 • 上一篇    下一篇

卫星云图的多通道FCM分割算法

王 伟1,刘 娟1,孟志斌1,郭钧天2   

  1. (1.武汉大学计算机学院,湖北 武汉 430072;2.国网电力科学研究院武汉南瑞有限责任公司,湖北 武汉 430074)
  • 收稿日期:2012-04-25 修回日期:2012-07-10 出版日期:2012-10-25 发布日期:2012-10-25

Multichannel FCM Segmentation Algorithm of  Satellite Cloud Image

WANG Wei1,LIU Juan1,MENG Zhibin1,GUO Juntian2   

  1. (1.School of Computer Science,Wuhan University,Wuhan 430072;2.Wuhan NARI Co.,Ltd.,State Grid Electric Power Research Institute,Wuhan 430074,China)
  • Received:2012-04-25 Revised:2012-07-10 Online:2012-10-25 Published:2012-10-25

摘要:

卫星云图是对地球大气进行遥感测量的重要资料,云团的识别、跟踪及预测都需要对卫星云图进行图像分割和边缘提取。本文通过改进模糊C均值(FCM)算法对云图进行分割,改进后的算法显示出了效率高、分辨准确的特点。实验采用了2011年6月的RGB多通道卫星云图,通过对云图分层聚类,提取多通道聚类的相交区域等过程,实现了云团快速准确的分割。

关键词: 卫星云图, 多通道, FCM, 分割

Abstract:

The satellite cloud images are important materials in the remote sensing measurement of the earth’s atmosphere. Cloud identification, tracking and prediction need segmentation and edge extracted operator on satellite cloud images. In this paper, we improve the fuzzy Cmeans (FCM) algorithm for cloud image segmentation. The experimental result demonstrates that the improved algorithm features efficiency and accuracy. In the experiment, we employ the RGB multichannel satellite cloud images in June 2011, cluster the cloud image on the layering of image, and extract multichannel clustering intersection areas, etc. The result achieves the fast and accurate segmentation to satellite cloud images.

Key words: satellite cloud images;multichannel;FCM;segmentation