Abstract: The paper presented a simple and fast color fusion method for night vision based on image enhancement and color transfer. Firstly, the contrast of infrared and low-light visible images was adjusted by local histogram equalization. And medium filter was applied to clean noises in the enhanced images. Then, the two enhanced images were fused into the three components of an RGB image in terms of a simple linear fusion strategy. To obtain false color images possessing a natural day-time color appearance, the paper suggested an approach which transferred color from the reference to the fused images in YUV color space. In this way, inappropriate color mappings were avoided and overall discrimination capabilities were enhanced. The experimental results based on three different data sets show that the final scene has a natural day-time color appearance. Furthermore, the fusion process is simple and fast.

Key words: image processing, image fusion, color transfer, color space

摘要： 提出了一种基于图像增强和颜色迁移理论的彩色夜视融合方法。首先采用局部增强技术以及中值滤波方法调整低光照可视图像和红外图像的对比度；然后将增强后的图像进行线性运算获得三幅灰度图像，并分别将其映射到RGB三个通道生成伪彩色融合图像；最后，基于YUV颜色空间将参考图像的颜色传输至融合图像获得自然、真实的彩色融合图像。实验结果表明，彩色迁移图像较伪彩色融合图像颜色更加自然、真实，更有利于人眼对目标和环境的判断识别。与其他融合方法相比，算法执行速度更快。

关键词: 图像处理, 图像融合, 颜色迁移, 颜色空间