基于多尺度Retinex的受云雾影响可见光图像增强研究  

Research on visible light image enhancement affected by cloud and fog based on multi-scale Retinex

作　　者：吴海丽 WU Haili(Department of computer science and technology,Taiyuan University,Taiyuan 030001,China)

机构地区：[1]太原学院计算机科学与技术系,太原030001

出　　处：《激光杂志》2023年第4期185-189,共5页Laser Journal

基　　金：全国高等院校计算机基础教育研究会项目(No.2022-AFCEC-501);山西省教科研规划办项目(No.HLW-20127);山西省科技厅软科学研究计划项目(No.2019041057-3)。

摘　　要：为增强云雾影响下的可见光图像质量,设计了基于多尺度Retinex的受云雾影响可见光图像增强方法。首先采用小波变换对受云雾影响可见光图像进行预处理,采用去噪算法消除可见光图像中的噪声,然后采用多尺度Retinex算法增强受云雾影响的可见光图像,最后进行可见光图像增强测试实验,实验结果表明,采用本方法处理后的可见光图像的对比度较为均衡,像素值处于1500 pixels左右,可以实现图像的整体增强。可见光图像的均值均与130极为接近,可见光图像平均梯度高于15,具有较高的实际应用价值。In order to enhance the quality of visible light image under the influence of cloud and fog,a visible light image enhancement method based on multi-scale Retinex is designed.Firstly,wavelet transform is used to preprocess the visible light image affected by clouds,and the denoising algorithm is used to eliminate the noise in the visible light image.Then the multi-scale Retinex algorithm is used to enhance the visible light image affected by clouds.Finally,the visible light image enhancement test experiment is carried out.The experimental results show that the contrast of the visible light image processed by this method is relatively balanced,and the pixel value is about 1500 pixels,It can enhance the whole image.The average value of visible image is very close to 130,and the average gradient of visible image is higher than 15,which has high practical application value.

关 键 词：云雾影响 可见光 图像质量 多尺度RETINEX算法 小波变换 

分 类 号：TN247[电子电信—物理电子学]