摘要
在原有的EMD算法基础上,利用多元EMD算法对遥感图像进行融合,该算法将图像看做多元变量,并将其投影到相应的方向向量上,从而获得相应的固有模式函数及残余分量。通过遥感全色图像与多光谱图像的融合证明该算法在既保持了光谱信息的同时,又增强了其空间细节。
A fusion scheme for multispectral image and panchromatic image is proposed based on original EMD(empirical mode decomposition)algorithm.To use multivariate EMD,firstly it look the image as multivariate,and project them into corresponding directional vectors,therefore it gets intrinsic mode functions and residual.At last,experiment is made and results show that this algorithm is not only preserve spectral information but also get a image containing more space details.
出处
《激光与红外》
CAS
CSCD
北大核心
2012年第7期837-840,共4页
Laser & Infrared
关键词
多元EMD
图像融合
方向向量
固有模式函数
multivariate emd
image fusion
directional vector
intrinsic mode function