基于局部能量的NSCT域红外与可见光图像融合算法

Novel fusion algorithm for infrared and visible images based on local energy in NSCT domain

提出了一种基于非下采样Contourlet变换(NSCT)的红外与可见光图像融合方法。首先对红外和可见光源图像进行多尺度、多方向分解;在低频系数上,采用基于局部能量比与基于局部能量加权相结合的方法进行融合;在高频系数上,定义了局部尺度方差的概念,并以局部尺度方差为测度进行取大融合;最后对融合系数进行重构得到融合图像。使用该算法对两类不同目的的红外与可见光图像进行了融合实验,实验结果表明,文中提出的算法在保留图像细节信息、增加信息量、方便目标检测方面都有显著地提高。

A fusion algorithm for infrared and visible images based on local energy and the nonsubsampled Contourlet transform （NSCT） was proposed. Firstly, the NSCT was performed on the infrared and visible images at different scales and directions. The low-frequency coefficients were fused with a hybrid rule that combine local energy ratio based rule and local energy weighted based rule. On the basis of defining the scale variance, the high-frequency coefficients were fused with a rule of maximum the scale variance. Finally, the fused coefficients were reconstructed to obtain the fused image. Two fusion experiments with different intentions were performed by using the proposed image fusion algorithm in this paper. The experimental results show that the algorithm gets more image details in the information, the amount of information increases significantly, and the target detection in the fused image is improved greatly.