增强融合图像视觉效果的图像融合方法  

Image Fusion Method for Enhancing Visual Effect of Fused Image

作　　者：荣传振 贾永兴 杨宇 朱莹 王渊 Rong Chuanzhen;Jia Yongxing;Yang Yu;Zhu Ying;Wang Yuan(Communications Engineering College,Army Engineering University of PLA,Nanjing,Jiangsu 210007,China)

机构地区：[1]陆军工程大学通信工程学院,江苏南京210007

出　　处：《信号处理》2019年第3期327-333,共7页Journal of Signal Processing

基　　金：江苏省自然科学基金项目(BK2012511)

摘　　要：针对现有图像融合方法得到的融合图像对比度低,图像纹理细节信息保留不充分,图像视觉效果差等问题,论文提出一种新的基于图像对比度增强的红外与可见光图像融合方法,以有效提高融合图像的视觉效果。首先,为提高可见光图像低亮度细节的能见度,在融合之前,提出一种基于引导滤波器的动态范围压缩与线性变换相结合的自适应图像增强方法;其次,采用基于引导滤波器和高斯滤波器相结合的多尺度融合方法,将红外图像信息有效地注入可见光图像中;最后运用非局部均值滤波对融合后的图像进行后处理,以得到效果增强的融合图像。实验结果表明,该方法能够获得较好的图像融合效果,无论从主观视觉还是客观评价指标上,都要优于现有的常用图像融合方法。The fused images obtained by the existing image fusion methods,often have low contrast,and retain the textural details insufficiently.In order to overcome the above problems,a new fusion method based on image contrast enhancement for the infrared and visible images is proposed in this paper.Firstly,in order to improve the visibility of low-light details of the visible image,an adaptive image enhancement method based on dynamic range compression and linear transformation is proposed;secondly,the infrared information is effectively injected into the visible image by using a novel hybrid multi-scale image fusion method based on the guided and Gaussian filters;finally,the fused image is post-processed by non-local mean filtering,so that the final fused image is more consistent with human visual perception.Experimental results show that the proposed method can obtain better image fusion results,and it is superior to the existing common used image fusion methods both in subjective and objective evaluation.

关 键 词：图像融合 图像增强 引导滤波 非局部均值滤波 多尺度分解 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]