Abstract: A novel fusion method is proposed for dynamic image which is based on the non-Gaussian statistical modeling of wavelet coefficients.Firstly，the source images are decomposed by Dual Tree Complex Wavelet Transform（DT-CWT） respectively.Then，the wavelet coefficients are modeled using the Generalized Gaussian Distribution（GGD）.Saliency measure，the weighted coefficient，is calculated by estimating distribution parameters.The pair of coefficients is fused through weighted average.Finally，the fused coefficients are reconstructed into a single fused image.The quality of the fused image is evaluated by three metric：Entropy，mutual information and Q^AB/F.The experimental results demonstrate that performance of the proposed method is prior to other two fusion approaches for infrared and visible dynamic image sequence.

Key words: image fusion, statistical model, dual tree complex wavelet transform, the generalized gaussian distribution, dynamic image

摘要： 针对动态红外和可见光图像融合，提出了一种新的基于统计模型的融合方法，即将图像的小波分解系数用广义高斯分布来建模。首先，源图像分别用双树复小波进行分解；然后，采用加权平均融合规则来进行小波系数的融合，其中加权系数由估计的广义高斯分布参数来计算；最后，将融合后的系数重构为一幅图像。融合图像采用熵、互信息和边缘保持度Q^AB/F来进行质量评价，实验结果表明方法的性能优于其他两种动态图像融合方法。

关键词: 图像融合, 统计模型, 双树复小波变换, 广义高斯分布, 动态图像