基于对比度金字塔与双边滤波的非对称红外与可见光图像融合  

Asymmetric Infrared and Visible Image Fusion Based on Contrast Pyramid and Bilateral Filtering

作　　者：杨九章 刘炜剑 程阳[1] YANG Jiuzhang;LIU Weijian;CHENG Yang(Key Laboratory of Biomimetic Robots and Systems,Ministry of Education,Beijing Institute of Technology,Beijing 100081,China)

机构地区：[1]北京理工大学仿生机器人与系统教育部重点实验室,北京100081

出　　处：《红外技术》2021年第9期840-844,共5页Infrared Technology

基　　金：国家自然科学基金项目(61905014);全国博管会博士后国际交流派出计划(20190097)。

摘　　要：为了同时保留红外图像的特征信息和可见光图像的细节信息,提出了一种基于对比度金字塔的非对称红外与可见光图像融合方法。首先,使用对比度金字塔对红外与可见光图像进行高频与低频信息分解,然后对高频部分采用绝对值取大方法进行融合,对于低频部分采用基于双边滤波的方法对红外与可见光图像进行非对称的处理;其次,使用对比度金字塔的逆变换得到融合后图像。对融合图像进行主观视觉和客观指标评价,结果表明该算法在突出目标特征信息和保留细节特征方面表现优异。This study proposes an asymmetric infrared and visible image fusion method based on a contrast pyramid to save the feature information of infrared image and the detail information of visible image simultaneously. First, the contrast pyramid is used to decompose the high-frequency and low-frequency information of the infrared and visible images;then, the high-frequency part is fused by taking the largest absolute value, and the low-frequency part is processed differently by the method based on bilateral filtering. Second, the inverse transform of the contrast pyramid was used to obtain the fused image. Subjective visual and objective index evaluations were conducted on the fused image. The results show that the algorithm performs well in highlighting the target feature information and retaining detailed feature information.

关 键 词：图像融合 红外图像 可见光图像 对比度金字塔 双边滤波 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]