摘要： 为能同时获得空间信息与光谱信息，提出一种基于非下采样Contourlet变换(NSCT)和脉冲耦合神经网络(PCNN)的遥感图像融合算法。通过NSCT分解得到多光谱与高分辨率图像，并对其高低频分量采用不同的准则进行融合。实验结果表明，该算法能较好地保留图像光谱信息，提高图像的空间分辨率。

关键词: 图像融合, 非下采样Contourlet变换, 脉冲耦合神经网络, 链接强度, 多光谱图像, 高分辨率图像

Abstract: In order to deal with the problem that the spatial information and spectrum information are hard to be combined when remote images are fused, this paper presents a remote sensing image fusion algorithm based on Nonsubsampled Contourlet Transform(NSCT) and Pulse Coupled Neural Network(PCNN). This algorthm uses different criteria to fuse the high and low frequency components of multi-spectral and high-resolution image which are decomposed by NSCT. Simulation results show that the proposed algorithm can effectively retain the image spectral information and improve the image spatial resolution greatly.

Key words: image fusion, Nonsubsampled Contourlet Transform(NSCT), Pulse Coupled Neural Network(PCNN), linking strength, multi-spectral image, high-resolution image

中图分类号: 

• TN911.73