首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于BP神经网络的风云四号遥感图像云检测算法
引用本文:高军,王恺,田晓宇,陈建.基于BP神经网络的风云四号遥感图像云检测算法[J].红外与毫米波学报,2018,37(4):477-485.
作者姓名:高军  王恺  田晓宇  陈建
作者单位:上海海事大学信息工程学院
基金项目:国家自然科学基金(F010408);上海市教育委员会、上海市教育发展基金会(13CG51)。
摘    要:通过对风云四号每两张相隔15分钟的图像进行分析,提出了归一化动云指数,加强数据集对低云、薄云及云系运动边缘的检测.在此基础上,提出了一种基于归一化动云指数的动态阈值法用于初步云检测,并进一步提出基于BP神经网络的云检测算法.实验结果表明,该算法可以消除阈值选取中的主观影响,在大范围复杂下垫面的遥感图像数据中可以取得较好的云检测效果.

关 键 词:云检测    遥感图像处理    风云四号    BP神经网络
收稿时间:2017/10/18 0:00:00
修稿时间:2018/1/21 0:00:00

A BP-NN based Cloud Detection Method for FY-4 Remote Sensing Images
GAO Jun,WANG Kai,TIAN Xiao-Yu and CHEN Jian.A BP-NN based Cloud Detection Method for FY-4 Remote Sensing Images[J].Journal of Infrared and Millimeter Waves,2018,37(4):477-485.
Authors:GAO Jun  WANG Kai  TIAN Xiao-Yu and CHEN Jian
Institution:College Of Information Engineering, Shanghai Maritime University,Shanghai Maritime University,Shanghai Maritime University and Shanghai Maritime University
Abstract:In this paper, normalized difference cloud moving index ( NDCM I) is put forw ard by analyzing the remote sensing data every 15 minutes. By applying NDCM I, the detection of low cloud, thin cloud and the edge of moving cloud can be enhanced. We proposed a dynamic threshold method w ith NDCM I for preliminary cloud detection, and then through the preliminary results, w e proposed a novel cloud detection method based on back propagation neural netw ork ( BP-NN) . The experimental results show that the proposed method can eliminate the subjectivity in threshold selection, and can achieve better cloud detection results for remote sensing image in complex situations.
Keywords:cloud detection  remote image processing  FY-4  back propagation neural network
本文献已被 CNKI 等数据库收录!
点击此处可从《红外与毫米波学报》浏览原始摘要信息
点击此处可从《红外与毫米波学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号