基于多尺度顶帽变换的红外与可见光图像融合

Fusion of Infrared and Visible Images Based on Multi-Scale Top-Hat Method

摘要: 针对传统多尺度图像融合方法容易弱化红外目标信息和降低图像对比度的问题，本文借助于形态学的优势和模糊规则的特性，提出一种简单、高效的红外与可见光图像融合算法。首先，使用多尺度形态学分离源图像高频成分和低频成分；其次，利用模糊规则整合低频成分，使用均值法合理注入图像高频成分；最后，经过形态学逆变换得到融合图像。实验结果表明，与传统融合方法相比，本文算法能够较好地保留可见光图像中的细节信息，突出红外目标信息。

Abstract: Aiming at the problem that the traditional multi-scale image fusion method is easy to weaken the infrared target information and reduce the image contrast, this paper proposes a fusion algorithm of infrared and visible image by virtue of the advantages of morphology and the characteristics of fuzzy rules. Firstly, multi-scale morphology was used to separate high-frequency and low-frequency components from source images. Secondly, the fuzzy rules were used to integrate the low frequency components, and the mean value method was used to inject the high frequency components reasonably. Finally, the fused image is obtained by morphological inverse transformation. Experimental results show that, compared with the traditional fusion method, the proposed algorithm can retain the detailed information in visible image and highlight the infrared target information.