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

基于人工免疫算法的光学影像与SAR影像配准方法
引用本文:冯甜甜,艾翠芳,王建梅,张绍明.基于人工免疫算法的光学影像与SAR影像配准方法[J].同济大学学报(自然科学版),2015,43(10):1588-1593.
作者姓名:冯甜甜  艾翠芳  王建梅  张绍明
作者单位:同济大学测绘与地理信息学院,同济大学测绘与地理信息学院,同济大学测绘与地理信息学院,同济大学测绘与地理信息学院
基金项目:国家“九七三”重点基础研究发展计划(2012CB719903);国家自然科学基金项目(41171327,41201379);教育部高等学校博士学科点专项科研基金(20120072120057); 同济大学青年优秀人才培养行动计划(2014KJ027)
摘    要:提出了一种基于人工免疫算法的光学影像和SAR影像配准方法,该方法从影像上的面状地物入手,仅从识别性较好的光学影像上提取面状地物,先随机给定一组配准参数,将光学影像上面状地物的坐标经仿射变换获得新的坐标,以转换后新坐标在SAR影像上对应区域的均质性为评价标准,并利用人工免疫算法对配准参数进行优化,从而得到影像配准结果.最后,利用WorldView-2和RadarSat-2影像的配准实验验证该方法的有效性,结果表明该方法配准精度可优于2像素.

关 键 词:光学影像  SAR影像  影像配准  人工免疫算法
收稿时间:2014/10/26 0:00:00
修稿时间:2015/7/26 0:00:00

A Novel Image Registration Method for Optical and SAR Satellite Images Based on Artificial Immunity Algorithm
FENG Tiantian AI Cuifang,WANG Jianmei,ZHANG Shaoming,AI Cuifang,WANG Jianmei and ZHANG Shaoming.A Novel Image Registration Method for Optical and SAR Satellite Images Based on Artificial Immunity Algorithm[J].Journal of Tongji University(Natural Science),2015,43(10):1588-1593.
Authors:FENG Tiantian AI Cuifang  WANG Jianmei  ZHANG Shaoming  AI Cuifang  WANG Jianmei and ZHANG Shaoming
Institution:College of Surveying and Geo informatics, Tongji University, Shanghai 200092, China,College of Surveying and Geo informatics, Tongji University, Shanghai 200092, China,College of Surveying and Geo informatics, Tongji University, Shanghai 200092, China and College of Surveying and Geo informatics, Tongji University, Shanghai 200092, China
Abstract:It is quite difficult to extract corresponding features from optical and SAR satellite images, since the intensities of objects from these two kinds of sensors are of great differences due to the different imaging bands. In this paper, a novel registration method for optical and SAR satellite images based on Artificial Immunity Algorithm (AIA) is proposed. Taking into account of sufficient spectral information from optical satellite image, areal features are extracted from optical image based on image classification strategy firstly. Second, affine transformation with initial transformation parameters is adopted to obtain the new coordinates of features according to the location of features in optical image. Thirdly, the transformation parameters are optimized based on AIA by using the homogeneity of corresponding areas in SAR image, which are determined by the new coordinates of areal features, as the criterion of the transformation parameters. WorldView-2 and RadarSat-2 images are used to verify the effect of proposed image registration method for optical and SAR satellite images. It is proved that the RMSE of image registration is less than 2 pixels.
Keywords:Optical image  SAR image  Image registration  AIA
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《同济大学学报(自然科学版)》浏览原始摘要信息
点击此处可从《同济大学学报(自然科学版)》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