北京航空航天大学学报 ›› 2011, Vol. 37 ›› Issue (4): 466-471.

• 论文 • 上一篇    下一篇

一种基于多通道卫星云图的台风分割方法

钱华明, 姜波   

  1. 哈尔滨工程大学 自动化学院, 哈尔滨 150001
  • 收稿日期:2010-05-28 出版日期:2011-04-29 发布日期:2011-04-29
  • 作者简介:钱华明(1965-),男,安徽池州人,教授,qianhuam@sina.com.
  • 基金资助:

    国防预研基金资助项目(40103 × × 302)

Method base on multi-channel satellite cloud image for typhoon segmentation

Qian Huaming, Jiang Bo   

  1. College of Automation, Harbin Engineering University, Harbin 150001, China
  • Received:2010-05-28 Online:2011-04-29 Published:2011-04-29

摘要: 有效的台风主体分割能够提高台风预报的准确性.提出一种基于矢量图像的改进水平集方法进行台风分割,将C-V模型推广到矢量空间,加入了无需重新初始化的能量项;提出了一种迭代收敛条件并设计了针对云图特点的模型参数及分割方法,该方法利用了多通道的云图信息,避免了无谓的迭代计算,能够加快分割曲线的演化速度并提高分割的准确性.实验结果验证了所提出方法的有效性和可行性,其平均目标错误率与平均非目标错误率分别为1.21%与2.25%,可得到较理想的台风分割效果.

Abstract: A modified level set method for typhoon segmentation base on vector image was proposed to improve the accuracy of typhoon prediction. The C-V model was extended to the vector space and an energy term without re-initialization was introduced. An iteration convergence condition was proposed,and the parameters of the model and the method of segmentation were designed for the features of cloud image. Through the use of cloud image information and avoiding the unnecessary iterative calculation, this method can accelerate the speed of curve evolution and improve the accuracy of segmentation. The experimental results verify the validity and feasibility of the proposed method. The expected typhoon segmentation effect is achieved with the average false target rate of 1.21% and the average false non-target rate of 2.25%.

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发