基于侧窗滤波与分块贝塞尔插值的图像融合  

Image Fusion Based on Side Window Filtering and Blocked Bezier Interpolation

作　　者：钱进 王永成[1] 徐东东[1] 贲广利 QIAN Jin;WANG Yong-cheng;XU Dong-dong;BEN Guang-li(Changchun Institue of Optics,Fine Mechanics and Physics,Chinese Academy of Science,Changchun 130033)

机构地区：[1]中国科学院长春光学精密机械与物理研究所,长春130033

出　　处：《长春理工大学学报（自然科学版）》2020年第3期7-12,共6页Journal of Changchun University of Science and Technology(Natural Science Edition)

摘　　要：为解决传统红外与可见光图像融合算法存在的目标信息不足、背景杂波以及边缘模糊等问题,提出一种基于侧窗滤波与分块贝塞尔插值法的红外与可见光图像融合算法。首先,采用基于分块的贝塞尔插值方法估计红外图像的背景,利用红外图像与估计的背景图像作差,获得目标图像。然后,对目标图像进行侧窗滤波处理,同时,利用红外图像与可见光图像作差,获得前景图像,滤波结果与前景图像叠加获得目标图像的增强结果。最终,目标增强结果与可见光图像叠加,获得最终融合结果。实验结果验证了所提融合算法在提升图像质量方面的性能较好。An infrared and visible image fusion algorithm based on Side Window Filtering(SWF)and Block Bezier Interpolation(BBI)was proposed to solve the problems of insufficient target information,background clutter and blurry edge in traditional infrared and visible image fusion algorithms.Firstly,the BBI method was utilized to reconstruct background from the infrared image,and a target image is obtained from the difference between infrared image and background.Then,the SWF algorithm is performed on the target image,and at the same time,the difference between the infrared image and the visible image is used to obtain the foreground image,and the result of SWF is superimposed with the foreground image to obtain the enhanced result of the target image.Finally,the target enhancement result is superimposed with the visible image to obtain the final fusion result.Experimental results show that the proposed fusion algorithm has better performance in improving image quality.

关 键 词：红外图像 图像融合 侧窗滤波 背景抑制 边缘保护 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]