基于深度估计的雾天模拟方法  

Fog Simulation Method Based on Depth Estimation

作　　者：李靓 叶青[1] 刘建平 刘宇泽 Li Liang;Ye Qing;Liu Jianping;Liu Yuze(School of Electrical and Information Engineering,Changsha University of Science and Technology,Changsha 410114,Hunan,China)

机构地区：[1]长沙理工大学电气与信息工程学院,湖南长沙410114

出　　处：《激光与光电子学进展》2023年第10期72-78,共7页Laser & Optoelectronics Progress

摘　　要：针对雾天图像数据集匮乏问题,提出一种基于深度估计的雾天模拟方法。自适应调整亮度与饱和度对清晰原图像进行预处理,采用自监督单目深度挖掘网络生成图像的深度图,利用引导滤波优化深度图,设定模拟图像能见度获得透射率图,通过暗通道图区分天空区域并估计大气光值,最终由大气散射模型得到设定能见度下的雾天模拟图像。实验数据显示,该方法有效改善了模拟图像目标不清晰、雾气边缘锐化问题,在模拟能见度为2000 m以下的雾天图像时效果稳定,其雾天模拟图像与真实雾天图像的特征评价指标平均误差率为6.28%,表明该方法具有可行性,可对自然环境下清晰图像进行雾天模拟以解决雾天图像数据集匮乏与能见度数据缺失的问题。A fog simulation method based on depth estimation is proposed,aiming at the lack of foggy image datasets.The brightness and saturation are adjusted adaptively to preprocess the clear original image,selfsupervised monocular depth mining network is used to generate the depth map and which is optimized by guided filtering.Transmittance map is obtained with setting the visibility of the simulated image,the dark channel map is used to distinguish sky area to estimate the atmospheric light value,and simulated foggy image with visibility is generated through the atmospheric scattering model.According to the experimental data,the problems of unclear targets in simulated images and sharpening of fog edges are improved effectively.The effect is stable when simulated foggy visibility is below 2000 m,which average error rate of feature evaluation index between simulated foggy image and real foggy image is 6.28%,which shows that the proposed method is feasible.It can simulate clear images in natural environment to solve the problems of lack of foggy image dataset and visibility data.

关 键 词：图像处理 雾天模拟 深度估计 自适应 大气光值 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]