基于暗通道先验和优化自动色阶的图像去雾算法  

IMAGE DEFOGGING ALGORITHM BASED ON DARK CHANNEL PRIOR AND OPTIMIZED AUTO-COLOR

作　　者：庄秀玲 谭福奎[2] 李震 李良荣 Zhuang Xiuling;Tan Fukui;Li Zhen;Li Liangrong(College of Big Data and Information Engineering,Guizhou University,Guiyang 550025,Guizhou,China;Department of Physics and Electronic Science,Xingyi Normal University for Nationalities,Xingyi 562400,Guizhou,China)

机构地区：[1]贵州大学大数据与信息工程学院,贵州贵阳550025 [2]兴义民族师范学院物理与电子科学系,贵州兴义562400

出　　处：《计算机应用与软件》2021年第7期190-195,共6页Computer Applications and Software

基　　金：国家自然科学基金项目(61361012);贵州省科技计划项目(黔科合平台人才[2017]5788号);2017年度兴义民族师范学院教授基金项目(17XYJS26)。

摘　　要：针对暗通道先验产生的图像深度边缘上的白色晕圈、天空区域失真等问题,提出基于暗通道先验和优化自动色阶的单图像去雾算法。引入改进暗通道先验对透射率进行导向滤波,精细化透射率传播图,利用加权最小二乘法保留图像边缘信息,以优化自动色阶增强图像。采用定性与定量分析相结合的方法对该算法和几种经典去雾算法进行评价,结果表明该算法能够在保持图像颜色质量的同时保留细节清晰,具有更好的视觉感知。Aiming at solving problems of white halo and sky region distortion on the edge of image depth generated by dark channel prior,this paper proposes a single image defogging algorithm based on dark channel prior and optimized auto-color.This algorithm introduced improved dark channel prior to get guided filtering of transmittance to refine the transmittance map,and used the weighted least square method to preserve the image edge information to optimize auto-color enhancement image.And the contrast via qualitative and quantitative analysis between the algorithm in this paper and several other classical defogging algorithms shows that this algorithm has a better visual perception in preserving color quality and keeping clear details of the image.

关 键 词：暗通道先验 透射率 加权最小二乘法 自动色阶 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]