基于NSCT和PCNN的红外与可见光图像融合方法  

Fusion Algorithm of Infrared and Visible Images Based on NSCT and PCNN

作　　者：李美丽[1,2] 李言俊[1] 王红梅[1] 张科[1] 

机构地区：[1]西北工业大学航天学院,西安710072 [2]西安石油大学理学院,西安710065

出　　处：《光电工程》2010年第6期90-95,共6页Opto-Electronic Engineering

基　　金：航空科学基金资助项目(20090153003);西北工业大学翱翔之星人才计划项目(R1129)

摘　　要：提出了一种基于非采样Contourlet变换(NSCT)和脉冲耦合神经网络(PCNN)的红外与可见光图像融合方法。首先用NSCT对已配准的源图像进行分解,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;对各带通子带系数提出了一种改进的基于PCNN的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逆变换得到融合图像。实验结果表明,本文方法优于Laplacian方法、小波方法和传统的NSCT方法。A fusion algorithm of infrared and visible images was proposed based on Nonsubsampled Contourlet Transform（NSCT） and Pulse Coupled Neural Networks（PCNN）.Firstly,two registered original images were decomposed by using NSCT separately,thus the low frequency subband coefficients and varieties of directional bandpass subband coefficients were obtained.Secondly,the selection principle of the low frequency subband coefficients was based on edges of images.The selection principle of the bandpass directional subband coefficients was improved by fusion method based on PCNN.Finally,the fused image was obtained by performing the inverse NSCT on the combined coefficients.The experimental results show that the proposed algorithm outperforms laplacian-based,wavelet-based and NSCT-based fusion algorithms.

关 键 词：图像融合 非采样CONTOURLET变换 脉冲耦合神经网络 链接强度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] TN911.73[自动化与计算机技术—计算机科学与技术]