非采样轮廓波变换下的红外与可见光图像融合

Infrared and Visible Image Fusion Based on NSCT

针对红外与可见光图像融合存在的边缘模糊、视觉效果不佳的问题,提出了一种改进的基于非下采样轮廓波变换(NSCT)的红外和可见光图像融合方法。首先采用NSCT对红外与可见光图像进行多尺度、多方向分解,然后对低频系数采用基于边缘的方法进行融合;对高频系数采用基于区域能量的方法进行融合。最后,通过NSCT反变换来获取融合图像。实验结果表明:文中改进算法得到的融合图像不仅边缘等细节部分更加清晰,而且在视觉效果上更加符合人眼视觉特性。

Aimed at the problems that the edge is fuzzy and the visual effect is poor during the fusion of the infrared and visible images, a fusion algorithm based on NSCT is proposed. NSCT has shift-invariance and a good direction selection, only thus can the algorithm fully capture the contour and more details of the im- age. Firstly, the NSCT is used to take multi-scale, multi-direction decomposition for the infrared and visible image, and then the edges of the low frequency image is extracted by using the isotropic Soble gradient operator ,and fused the low frequency coefficients by edge information to attain the low frequency fusion image. Meanwhile, the high frequency coefficients are fused by region energy to attain the high frequency fusion image. Finally, the fusion image is reconstructed by performing the inverse NSCT on the low frequency fusion image and the high frequency fusion image. The simulation experiments according to both the subjective and objective criteria ,including the information entropy , space frequency and average gradi- ent, show that the algorithm can get a good fusion image with more clearly details such as edges. Besides , the fusion image is more conform to the requirements of human vision.