基于引导滤波与双树复小波变换的红外与可见光图像融合

Infrared and Visible Image Fusion with Guided Filtering and Dual-Tree Complex Wavelet Transform

针对传统图像融合算法目标不突出、边缘及纹理细节不清晰或缺失、对比度降低等问题,提出一种基于引导滤波(GF)和双树复小波变换(DTCWT)的红外与可见光图像融合算法。首先,根据红外与可见光图像的特点,在DTCWT分解前对可见光图像进行GF增强,同时对经DTCWT分解后的红外高频分量进行GF增强;然后,根据不同频带系数特点,提出一种基于显著性的自适应加权规则对红外与可见光低频子带分量进行融合,采用一种基于拉普拉斯能量和(SML)与梯度值向量的规则对不同尺度、方向下高频子带进行融合;最后,对融合后的高、低频系数进行DTCWT逆变换以得到最终重构图像。将所提算法与6种高效融合算法进行对比评价,实验结果表明,所提融合算法在不同场景下具有显著的目标特征,同时背景纹理和边缘细节清晰,整体对比度适宜,并且在4类客观评价指标上也取得了较好的效果。

Traditional image fusion algorithm has limitations,such as indistinct target,unclear or missing edge and texture details,and reduced contrast.An infrared and visible image fusion algorithm based on a guided filter(GF)and dualtree complex wavelet transform(DTCWT)is proposed.First,GF enhancement is performed on visible and highfrequency infrared image components before and after DTCWT decomposition,respectively,according to the characteristics of infrared and visible images.Then,according to the characteristics of different frequency band coefficients,an algorithm based on saliency adaptive weighting rules is proposed to fuse infrared and visible lowfrequency subband components;further,a rule based on Laplace energy sum(SML)and gradient value vector is used to fuse highfrequency subbands at different scales and directions.Finally,the fused high-and lowfrequency coefficients are inverted using DTCWT to obtain the final reconstructed image.The proposed algorithm is compared with six efficient fusion algorithms.The experimental results demonstrate the improved performance of the proposed algorithm across four objective evaluation indicators with significant target features in different scenes,clear background texture and edge details,and appropriate overall contrast.