基于YUV颜色模型与导向滤波的图像去雾算法  

Image defogging algorithm based on YUV color model and guided filtering

作　　者：何惜琴[1] 陈冬冬 HE Xi-qin;CHEN Dong-dong(College of Electronic and Electrical Engineering, Minnan University of Science and Technology, Quanzhou 362700, China)

机构地区：[1]闽南理工学院电子与电气工程学院,福建泉州362700

出　　处：《液晶与显示》2021年第8期1166-1173,共8页Chinese Journal of Liquid Crystals and Displays

基　　金：福建省教育厅中青年教师科研项目(No.JAT190888,No.JAT200739);泉州市高层次人才团队(No.2019CT003)。

摘　　要：针对去雾过程中容易出现色彩过饱和与偏色现象的问题,提出一种基于YUV颜色模型和导向滤波的图像去雾算法。首先分离出含雾图像的亮度分量,结合拉普拉斯锐化算子与导向滤波细化大气光幕,求得准确的透射率之后,对天空区域进行修正;其次根据光幕值的强度信息定位浓雾区域,将该区域平均值作为大气光的估计;最后对色度分量进行补偿,还原真实场景的色彩饱和度。实验结果表明,去雾后图像的边缘强度与颜色保真度得到大幅提升,信息熵、平均梯度和标准差客观评价参数均优于目前主流的算法。该算法去除雾气的效果显著,能满足图像视见度和细节清晰度的需求。Aiming at the problem of color over-saturation and color cast in the process of defogging,an image defogging algorithm based on YUV color model and guided filtering is proposed.Firstly,the brightness component of the fog image is separated,and the atmospheric veil is refined by combining Laplace sharpening operator and guided filtering to obtain the accurate transmittance,and then the sky area is corrected.Secondly,the dense fog area is located according to the intensity information of the atmospheric veil,and the average value in this area is used as the estimation of airlight.Finally,the chromaticity component is compensated to restore the color saturation of the real scene.The experimental results show that the edge intensity and color fidelity of the image after defogging are greatly improved,and the objective evaluation parameters of information entropy,average gradient and standard deviation are better than the current mainstream algorithms.The proposed algorithm demonstrates that the effect of defogging is remarkable,which can meet the requirements of image visibility and detail clarity.

关 键 词：图像去雾 图像复原 YUV颜色模型 导向滤波 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]