Abstract: An image fusion method based on LLF and RBD is proposed. In order to make full use of the target information of the infrared image and the detail information of the visible image, local Laplacian filters are used to smooth the infrared image and enhance the visible image. On this basis, RBD is used to process the infrared image for detecting the target better. In addition, in order to enhance the target information, reduce the background interference, the result of RBD is transformed by S curve. Then, the infrared and visible images are decomposed into high frequency and low frequency components by NSST. Finally, the low-frequency components are fused with saliency map obtained by S transform and the high-frequency components are fused with the rule of large absolute value. The experimental results show that the fusion method can get the fusion image of the infrared target highlight and the detail enhancement.

Key words: image fusion, Nonsubsampled Shearlet Transformation（NSST）, saliency optimization from Robust Background Detection（RBD）, Local Laplacian Filters（LLF）, transformation of S curves

摘要： 提出一种基于LLF和RBD检测的红外和可见光图像融合方法。运用局部拉普拉斯滤波对红外图像平滑处理和对可见光增强处理，以充分利用红外图像的目标信息和可见光图像的细节信息。在此基础上，采用增强背景检测的RBD显著性检测算法处理红外图像，以很好地检测出目标。此外，为了增强目标信息，减弱背景干扰，对RBD检测的结果进行S曲线变换。然后，对红外和可见光图像应用NSST分解得到高频分量与低频分量。最后，使用S曲线变换后获得的显著图对低频分量进行加权融合，采用绝对值取大的规则对高频分量进行融合。实验结果表明，该方法能够得到红外目标突出，细节增强的融合图像。

关键词: 图像融合, 非下采样Shearlet变换（NSST）, 增强背景检测的显著性优化（RBD）, 局部拉普拉斯滤波（LLF）, S曲线变换