基于H-NL-MTV模型的单幅彩色图像去雾  

Single Color Image Dehazing Based on the Basis of H-NL-MTV Model

作　　者：魏伟波 李帅 潘振宽 侯国家 赵胜楠 WEI Weibo;LI Shuai;PAN Zhenkuan;HOU Guojia;ZHAO Shengnan(School of Computer Science and Technology,Qingdao University,Qingdao 266071,Shandong,China)

机构地区：[1]青岛大学计算机科学技术学院,山东青岛266071

出　　处：《华南理工大学学报（自然科学版）》2018年第12期34-41,50,共9页Journal of South China University of Technology(Natural Science Edition)

基　　金：国家自然科学基金资助项目(61772294);山东省自然科学基金资助项目(ZR2017PF003)~~

摘　　要：基于暗原色先验理论的算法可以对不同场景下的雾天图像进行有效去雾,但是去雾后图像通常含有较多噪声.而非局部MTV模型(Non-Local Multi-Channel Total Varia-tion)可以用于彩色图像去噪,同时又具有良好的保持边缘作用,并且对含有纹理的彩色图像去噪后依然能保留原有的纹理特征.文中将这两种方法结合在一起,提出新的图像去雾算法,首先建立大气光值与大气传输函数相关的能量泛函(H-NL-MTV模型),然后利用交替方向乘子法引入辅助变量求解能量泛函,最后利用MATLAB软件进行仿真实验.仿真结果表明,该模型得到的图像清晰自然,图像边缘保持良好,纹理特征得到保留.The algorithm based on dark channel prior can effectively dehaze the hazy images in different scenes,but the dehazed images usually contain more noise.Non-local Multi-Channel Total Variation(NL-MTV)can be used to denoise color images while maintaining edge-preserving effects and the original texture can be preserved after denoising.In this paper,a new image dehazing algorithm is proposed by combining these two methods.Firstly,we establish the energy functional of the atmospheric light with atmospheric transport function(H-NL-MTV model)and use Alternating Direction Method of Multipliers by introducing auxiliary variables to solve the energy functional,and finally use MATLAB software to simulate experiment.The data results show that the image obtained by the proposed algorithm is clear and natural,and that the edges of the image are kept well,and that the texture features are preserved.

关 键 词：图像去雾 暗原色先验 非局部MTV模型 大气光值 大气传输函数 能量泛函 交替方向乘子法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]