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。
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.
出处
《遥感技术与应用》
CSCD
北大核心
2010年第5期604-608,共5页
Remote Sensing Technology and Application
关键词
可见光遥感图像
多尺度特征
特征提取
无监督分类
Optical remote sensing images
Multiscale features
Feature extracting
Unsupervised classifica-tion