提出了一种改进的基于多尺度变换的红外和可见光图像融合算法。首先, 用形态学帽变换对两幅已经配准的红外图像和可见光图像进行处理, 然后将处理后的图像分别进行轮廓波分解得到一系列的高频图像和低频图像。由于高频图像和低频图像特点的不同, 对高频图像采用平均梯度进行融合, 对低频图像采用PCA的方法进行融合。实验表明, 该方法很好地结合了形态学帽变换、主成分PCA算法和轮廓波变换的优点。与传统的融合方法相比, 提出的融合方法可以提供丰富的图像信息和清晰纹理细节, 且很好地保证了主要目标的亮度基本不变。

In this paper, an improved fusion algorithm for infrared and visible images using multi-scale analysis was proposed. First of all, Morphology--Hat transform was used for an infrared image and a visible image separately. Then the two images were decomposed into high-frequency and low-frequency images by contourlet transform. The image fusion method of high-frequency images is based on mean gradient and the image fusion method of low-frequency images is based on PCA (Principal Component Analysis). The experiments and results demonstrate that the proposed method can significantly improve image fusion performance, accomplish notable target information and high contrast and preserve rich details information at the same time.