首页 | 本学科首页   官方微博 | 高级检索  
     

基于高斯金字塔的遥感云图多尺度特征提取
引用本文:周全,张荣,尹东. 基于高斯金字塔的遥感云图多尺度特征提取[J]. 遥感技术与应用, 2010, 25(5): 604-608. DOI: 10.11873/j.issn.1004-0323.2010.5.604
作者姓名:周全  张荣  尹东
作者单位:(中国科学技术大学电子工程与信息科学系信息处理中心,安徽 合肥 230027 )
摘    要:提出了一种针对可见光遥感图像云图的多尺度特征提取方法。该方法通过高斯金字塔将遥感云图分解到多尺度空间,以此为基础将图像的灰度特征进行多尺度延拓,从而得到图像的多尺度特征矢量。实验结果表明在相同的特征算法和分类器条件下,多尺度延拓能够提升分类精度,更加有效地实现云图和地物的分类。

关 键 词:可见光遥感图像  多尺度特征  特征提取  无监督分类  
收稿时间:2010-03-19

The Extracting of Multiscale Features of Remote Sensing Cloud Images Based on Gaussian Pyramid
ZHOU Quan,ZHANG Rong,YIN Dong. The Extracting of Multiscale Features of Remote Sensing Cloud Images Based on Gaussian Pyramid[J]. Remote Sensing Technology and Application, 2010, 25(5): 604-608. DOI: 10.11873/j.issn.1004-0323.2010.5.604
Authors:ZHOU Quan  ZHANG Rong  YIN Dong
Affiliation:(Information Processing Center,University of Science and Technology of China,Hefei 230027,China)
Abstract:A method used for extracting multiscale features is applied to the optical remote sensing cloud im-ages.They are decomposed to multiscale space and the features of images are expanded during the process,from which a multiscale feature vector can be acquired.Provided identical feature algorithm and classifier,it is illustrated by experiment that multiscale expanded features can help raise the precision of classification,from which better performance of classifying clouds and earth targets can be achieved.
Keywords:Optical remote sensing images  Multiscale features  Feature extracting  Unsupervised classifica-tion  
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《遥感技术与应用》浏览原始摘要信息
点击此处可从《遥感技术与应用》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