首页 | 官方网站   微博 | 高级检索  
     

遥感图像变化检测算法研究
引用本文:余银峰,贾振红,覃锡忠,杨杰,庞韶宁.遥感图像变化检测算法研究[J].计算机工程与应用,2011,47(25):168-170.
作者姓名:余银峰  贾振红  覃锡忠  杨杰  庞韶宁
作者单位:1.新疆大学 信息科学与工程学院,乌鲁木齐 8300462.上海交通大学 图像处理与模式识别研究所,上海 2002403.奥克兰理工大学 知识工程与开发研究所,新西兰 奥克兰 1020
基金项目:科技部国际科技合作项目(No.2009DFA12870)~~
摘    要:提出了一种基于非下采样Contourlet变换和脉冲耦合神经网络的无监督的不同时相的卫星影像的变化检测新算法。该算法将非下采样Contourlet变换和脉冲耦合神经网络这两种方法结合,将它应用于不同时相的卫星影像的变化检测。实验结果表明,与传统方法相比,对于高斯和斑点噪声,该算法具有更高的抗噪性能和检测精确度。

关 键 词:非下采样Contourlet变换  脉冲耦合神经网络  无监督变化检测  多时相卫星影像  遥感  
修稿时间: 

Change detection algorithm in satellite images
YU Yinfeng,JIA Zhenhong,QIN Xizhong,YANG Jie,PANG Shaoning.Change detection algorithm in satellite images[J].Computer Engineering and Applications,2011,47(25):168-170.
Authors:YU Yinfeng  JIA Zhenhong  QIN Xizhong  YANG Jie  PANG Shaoning
Affiliation:1.College of Information Science and Engineering,Xinjiang University,Urumqi 830046,China2.Institute of Image Processing and Pattern Recognition,Shanghai Jiaotong University,Shanghai 200240,China3.Knowledge Engineering and Discovery Research Institute,Auckland University of Technology,Auckland 1020,New Zealand
Abstract:An unsupervised change detection algorithm in multi-temporal satellite images based on nonsubsampled Contourlet transform and pulse coupled neural network is proposed.This method makes a combination of both nonsubsampled Contourlet transform and pulse coupled neural network,and applies it to change detection initially.Experimental results demonstrate that the proposed method has a higher stability and accuracy against Gaussian and speckle noise compared with traditional algorithms.
Keywords:Nonsubsampled Contourlet Transform(NSCT)  Pulse Coupled Neural Network(PCNN)  unsupervised change detection  multi-temporal satellite images  remote sensing  
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《计算机工程与应用》浏览原始摘要信息
点击此处可从《计算机工程与应用》下载全文
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-23

京公网安备 11010802026262号