基于色彩空间和暗原色先验图像融合去雾算法  

An Image Fusion Defogging Algorithm Based on Color Space and Dark Primary Color Priori

作　　者：王超 刘文超[1,2] 翟海祥 何涛 王正家[1,2] WANG Chao;LIU Wenchao;ZHAI Haixiang;HE Tao;WANG Zhengjia(School of Mechanical Engineering Hubei University of Technology,Wuhan 430000 China;Hubei Key Laboratory of Modern Manufacturing Quality Engineering,Wuhan 430000 China)

机构地区：[1]湖北工业大学机械工程学院,武汉430000 [2]现代制造质量工程湖北省重点实验室,武汉430000

出　　处：《电光与控制》2022年第10期44-50,共7页Electronics Optics & Control

基　　金：国家自然科学基金(51275158)。

摘　　要：针对图像去雾算法效果不佳、处理效率低的问题,提出图像融合快速去雾算法。首先对原图降采样处理,减小图像尺寸,拷贝两份图像,然后分别转换到HSV色彩空间。针对转换后的第一份图像,降低v分量,提高透射率准确度;针对转换后的第二份图像,对v分量进行自适应处理、对s分量线性拉伸,提高图像色彩饱和度;接着将处理后的图像转回到RGB色彩空间,对转换后的第一份图像进行改进的暗通道算法去雾、直方图拉伸。最后对融合后的两份图像重采样。实验结果表明,去雾后的图像主观上视觉效果好,客观上算法复杂度降低,峰值信噪比、结构相似性、信息熵、标准差显著提高,证明算法有效。Aiming at the problems of poor effect and low processing efficiency of image defogging algorithms a fast defogging algorithm based on image fusion is proposed.Firstly the original image is down-sampled to reduce the image size.The original image is copied to produce two images and then the two images are converted to HSV color space respectively.For the first converted image the v component is reduced and the accuracy of transmittance is improved.For the second converted image the v component is adaptively processed and the s component is linearly stretched to improve the image color saturation.Then the processed images are re-converted to RGB color space.The first re-converted image is defogged by using the improved dark channel algorithm and then histogram stretched.Finally the two fused images are resampled.The experimental results show that the image after defogging has good subjective visual effect.Objectively the complexity of the algorithm is reduced and the Peak Signal-to-Noise Ratio(PSNR)Structural Similarity(SSIM)Information Entropy(IE)and Standard Deviation(SD)are significantly improved which verify the effectiveness of the algorithm.

关 键 词：图像融合 高斯滤波 图像增强 色彩空间 下采样 暗通道去雾 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]