基于Retinex的自适应水域图像去雾算法  

Adaptive water image defogging algorithm based on Retinex

作　　者：苏丽[1] 张丽君 SU Li;ZHANG Lijun(College of Intelligent Systems Science and Engineering,Harbin Engineering University,Harbin 150001,China)

机构地区：[1]哈尔滨工程大学智能科学与工程学院,黑龙江哈尔滨150001

出　　处：《应用科技》2024年第4期62-68,共7页Applied Science and Technology

基　　金：工业和信息化部高技术船舶科研项目(CJ01N20).

摘　　要：针对利用Retinex理论对水域雾天图像去雾时出现去雾不彻底、色彩失真等问题,提出一种基于Retinex的自适应水域图像去雾算法,通过分析水域雾天图像特征,提出水域雾气浓度划分标准,实现自适应去雾。将水域雾天图像由RGB颜色空间转到HSI颜色空间,对亮度(Intensity,I)分量进行拉伸变换以调节亮度平衡,再用改进的单尺度Retinex(singal scale Retinex,SSR)算法对I分量进行增强处理,初步提高图像清晰度;将增强处理后的图像转换回RGB颜色空间进行自适应伽马变换增强,进一步提高图像的清晰度及对比度;利用HSI颜色空间进行图像饱和度补偿及其他操作实现对水域雾天图像的色彩恢复。实验结果表明,该算法能有效进行自适应水域雾天图像去雾,色彩恢复真实,可得到细节清晰的高质量去雾图像。Aiming at the problems such as incomplete defogging and color distortion in water fog images using Retinex theory,this paper presents an adaptive water image defogging algorithm based on Retinex.By analyzing the features of water fog images,the water fog concentration division standard was proposed to realize adaptive defogging.The water fog image was transferred from RGB color space to HSI color space,the Intensity(I)component was stretched to adjust the brightness balance,and the improved Singal Scale Retinex(SSR)algorithm was used to enhance the I component to initially improve the image sharpness.Then the enhanced image was converted back to RGB color space for adaptive gamma-transform enhancement to further improve the clarity and contrast of the image.Image saturation compensation and other operations were carried out by HSI color space to realize color restoration of water fog images.The experimental results show that the algorithm can effectively remove fog in the adaptive water fog image,restore true color,and obtain clear and high-quality fog removal images.

关 键 词：RETINEX 雾气浓度划分 自适应去雾 HSI颜色空间 引导滤波 自适应伽马变换 饱和度补偿 色彩恢复 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]