基于非下采样Contourlet系数局部特征的遥感图像融合方法

Remote Sensing Image Fusion Method Based on Local Feature of Nonsubsampled Contourlet Coefficients

根据多光谱图像和全色图像非下采样Contourlet变换(NSCT)后低频子带和高频方向子带不同的融合目的,提出了一种基于NSCT系数局部特征的遥感图像融合方法。首先将全色图像和多光谱图像的I分量进行NSCT变换,在低频子带采用有选择的加权求和规则,对于高频方向子带系数,在最高分解层上,采用高频方向子带系数绝对值较大的算子,而在其它的分解层,根据高频方向子带系数的区域方差,比较一定区域内各个系数区域方差的大小,采用有选择的融合方法,然后对融合的高频方向子带系数进行一致性检验。实验表明:融合图像在最大限度保持源图像光谱信息的同时,其清晰度较其它的融合方法得到了较大的提高。

We proposed a remote sensing image fusion method based on the local feature of NSCT coefficients according to the different fusion purpose of lowpass sub-band and highpass sub-bands decomposed from the multispectral and panchromatic images by using Nonsubsampled Contourlet Transform（NSCT）.Firstly,we decomposed the I component of multispectral image and qanchromatic image into multi-resolution representation by using NSCT.Then,in the lowpass sub-band,the method of selective weighted summation was used.In the highpass sub-bands,we employed the algorithm taking the larger absolute value of sub-band coefficients at the highest decomposition level,and the selective method by comparing the region variance of sub-band coefficients in a fixed region at other decomposition levels.Finally,consistency check was implemented for the fused coefficients of highpass sub-bands.The experimental results show that the fusion image not only keeps the spectrum information of source image well,but image resolution has been greatly improved compared to other fusion methods.