一种基于非采样Contourlet变换红外图像与可见光图像融合算法

针对同一场景红外图像与可见光图像的融合问题,提出了一种基于非采样Contourlet变换(Nonsubsampled Contourlet Transform,NSCT)图像融合算法.算法首先采用NSCT对源图像进行多尺度、多方向分解,得到低频子带系数和各带通方向子带系数.然后,针对低频子带系数的选择,提出了一种基于红外图像与可见光图像物理特征的"加权平均"系数选择方案;针对各带通方向子带系数的选择,结合人眼视觉特性,提出了一种基于区域能量匹配的系数选择方案,得到融合图像的NSCT系数.最后经过NSCT逆变换得到融合图像.实验结果表明该算法可获得较理想的融合图像,其融合效果优于传统的基于离散小波变换以及离散小波框架变换的图像融合算法.

FUSION OF INFRARED AND VISIBLE LIGHT IMAGES BASED ON NONSUBSAMPLED CONTOURLET TRANSFORM

Focusing on the fusion problem of infrared and visible light images with the same scene,a novel multi-sensor image fusion algorithm based on the nonsubsampled contourlet transform(NSCT)was proposed.Firstly,the NSCT was performed on the source images at different scales and directions,thus the low frequency subband coefficients and varieties of directional bandpass subband coefficients were obtained.Secondly,for the low frequency subband coefficients,a 'weighted averaging' scheme based on the physical features of infrared images and visible light images was presented;while for the bandpass directional subband coefficients,a selection principle based on the local energy matching was developed,which was also consistent with the characteristics of the human vision system.Finally,the fused image was obtained by performing the inverse NSCT on the combined coefficients.Quantitative and qualitative analysis of the experimental results demonstrate that the proposed approach performs significantly better than the traditional methods based on the discrete wavelet transform and the discrete wavelet frame transform.