摘要
以全色和多光谱遥感图像为研究对象,提出一种基于非下采样Contourlet变换(NSCT)和自适应脉冲耦合神经网络(PC-NN)的遥感图像融合方法;该方法首先对全色图像和进行过IHS变换的多光谱图像的亮度分量进行NSCT变换,得到低频子带系数和各带通子带系数;其次对低频子带系数采取一种基于边缘的方法以得到融合图像的低频子带系数;然后采用以各带通子带系数的梯度作为PCNN的链接强度β的PCNN图像融合方法来确定融合图像的各带通子带系数;最后经过NSCT逆变换和IHS逆变换得到融合图像;实验结果表明,此方法更好地保留了原遥感图像中的有用信息,并提高了融合图像的质量。
Regarding the full--colour image and multispectral image as the research subject, We propose a new algorithm of remote sens ing image which combines NSCT and self--adaptive PCNN. Firstly, we perform the NSCT transform to luminance component of full--colour image and multispectral image which had transformed IHS to obtain coefficients of low frequency and high frequency. Secondly , we perform the wavelet decomposition to obtain the coefficient of low frequency of remote sensing image, then obtain the coefficient of high frequency of remote sensing image by self--adaptive PCNN, Finally , it can obtain a fused image by taking inverse NSCT and inverse IHS to reconstruct images. The results of simulation and quantifying evaluation show that this algorithm can preserve more useful information from the original remote sensing images effectively, and enhance the quality of the fused image.
出处
《计算机测量与控制》
CSCD
北大核心
2012年第5期1344-1346,共3页
Computer Measurement &Control
基金
国家自然科学基金(61062003
60803033)
作者简介
符强（1976-），男，讲师，主要从事图像及信息处理方向的研究。
