基于二维经验模态分解和高斯模糊逻辑的红外与可见光图像融合

针对传统多尺度图像融合方法容易损失可见光图 像细节、弱化红外目标信息和降低图像对比度的 问题,基于二维经验模态分解(BEMD)和高斯模糊逻辑(GFL)的特性,提出了一种红 外与可见光 图像融合的算法。首先,使用BEMD对源图像进行分解,得到图像的本征模(高频成分)和 趋势项(低频 成分)；其次,用GFL对趋势项进行恰当的融合,使用基于邻域特征的区域对比度法融合图 像的本征模； 最后,通过BEMD逆变换得到融合图像。实验结果表明,与传统的多尺度融合方法相比,在 主观上视觉上, 本文融合算法能够更有效地保留源可见光图像中的细节信息,并突出红外图像中的目标信息 ,提高融合图 像的质量；在客观评价指标上,本文融合算法的结果在信息熵(IE)、标准差(SD)、平均梯度(AG)、互 信息(MI)和空间频率(SF)5个客观指标上明显优于传统的多尺度融合方法。

Fusion of infrared and visible images based on BEMD and GFL

The traditional image fusion methods based on multi-scale transform can easily loss the details of visible image,weaken the infrared target information and reduce the image contrast.To solve the problem,a fusion method of infrared and visible images is proposed based on bidimensional empiric al mode decomposition(BEMD)and Gaussian fuzzy logic (GFL).Firstly,the source images are decompose d to obtain intrinsic modes(high-frequency component) and trend terms(low-frequency component)by BEM D.Secondly,trend terms are combined properly by using the GFL based fusion rule,and intrinsic modes are me rged by using regional contrast method based on neighborhood characteristics.Finally,the fusion image is obtai ned by performing the inverse BEMD transform on the combined coefficients.The experimental results prove t hat the proposed method outperforms the traditional multi-scale methods for infrared-visible images fu sion.Subjectively,the proposed fusion method can improve the quality of fusion image by preserving the details of source visible image and highlighting the targets of source infrared image.Objectively,the results of t he proposed fusion method are obviously better than those of the traditional multi-scale methods in the objec tive evaluation values,such as information entropy (IE),standard deviation (SD),average gradient (AG),mutual information (MI) and spatial frequency (SF).