结合FABEMD和改进的显著性检测的图像融合

Image fusion combining FABEMD with improved saliency detection

针对红外与可见光图像融合中存在的显著目标不突出、对比度低、存在较多的伪影问题,提出了一种结合快速自适应二维经验模态分解(fast and adaptive bidimensional empirical mode decomposition,FABMED)和改进的显著性检测的图像融合算法。首先,通过FABEMD对红外和可见光图像进行多尺度分解得到对应的基础层和细节层。然后,对最大对称环绕显著性检测做暗抑制改进,将其用于基础层的融合上;结合改进的显著性检测和引导滤波,对细节层进行融合。最后,对各融合子图进行FABEMD逆变换重构出融合图像。与其他经典的融合算法相比,仿真实验验证了本文算法的有效性。

Aiming at the problem that the significant targets are not prominent,the contrast is low,and there are many artifacts in infrared and visible image fusion,an image fusion algorithm combining fast and adaptive bidimensional empirical mode decomposition(FABMED)with improved visual saliency detection is proposed.First,the multi-scale decomposition of infrared and visible images is performed by FABEMD to obtain the corresponding base layer and detail layers.A dim suppression improvement is then performed on the maximum symmetric surround saliency detection,which is used for the fusion of the base layer.Combined with the improved saliency detection and guided filter,the detail layers are fused.To this end,the inverse FABEMD transform on each fusion sub-image is performed to reconstruct the fused image.Compared with other typical fusion algorithms,the simulation experiments verify the effectiveness of the proposed algorithm.