针对传统可见光图像与红外图像融合存在显著性信息保留不完整的问题，本文提出了一种新的自适应加权平均融合算法。首先，该方法通过非下采样轮廓波变换将源图像分解为不同尺度、不同方向的高低频分量。然后，针对低频分量的特点提出了一种基于显著性的自适应加权平均融合规则，用于保留源图像中的重要信息。对于高频分量，本文采用绝对值取大的融合策略。最后，根据融合后的高低频分量重构出最终的融合图像。实验结果表明，本文算法与传统融合算法相比，在主观视觉和客观指标上都具有优势。

Traditional fusion methods of infrared and visible images have difficulties in completely preserving the saliency information from source images. In order to overcome these problems, this paper proposed a novel image fusion method based on adaptive weighted average. Firstly, the non-subsampled contourlet transform (NSCT) is applied to decompose the source images into low-frequency and high-frequency coefficients. To preserve the salient information of source images, a novel fusion rule of low-frequency coefficients is designed according to the characteristics of infrared and visible images. The “max-absolute” scheme is employed on high-frequency coefficients. Finally, the fused image is reconstructed by applying the inverse NSCT on the fused low-frequency and high-frequency coefficients. The experimental results show that the proposed method has advantages in both subjective and objective evaluations.