基于自适应容差优化的暗通道去雾算法  

Dark channel defogging algorithm based on adaptive tolerance

作　　者：郭鑫 于萍[1] 王岩 司振惠 GUO Xin;YU Ping;WANG Yan;SI Zhen-hui(School of Computer Science,Jilin Normal University,Siping 136000,China;Siping Educational Technology Equipment Center,Siping 136000,China)

机构地区：[1]吉林师范大学计算机学院,吉林四平136000 [2]四平市教育技术装备中心,吉林四平136000

出　　处：《计算机工程与设计》2023年第5期1471-1478,共8页Computer Engineering and Design

基　　金：国家自然科学基金面上基金项目(62972384);吉林省教育厅科学技术研究基金项目(JJKH20210458KJ);吉林省发展和改革委员会创新能力建设基金项目(2021C038-7)。

摘　　要：针对暗通道先验理论对透射率、大气光值估计不准确及去雾后图像亮度降低等问题,提出一种算法。在暗通道先验理论的基础上,利用引导滤波对有雾图像进行平滑,通过限制对比度自适应直方图均衡化算法处理平滑后的图像,恢复由于雾产生的色差,选取较为准确的大气光值;引入Brenner清晰评价标准自适应确定容差值,实现对透射率的修正;将有雾图像与清晰图像加权融合,保存图像更多细节;在YUV颜色空间中调节亮度分量Y,改善图像亮度。实验结果表明,该算法可有效改善有雾图像的亮度过高与清晰度过低的问题,与其它算法相比,在保留图像细节处相对更完整,图像整体去雾效果更佳。Aiming at the problems of inaccurate estimation of transmittance,atmospheric light value and image brightness reduction after defogging by dark channel prior theory,an algorithm was proposed.Guided filtering was used to smooth the foggy image on the basis of the dark channel prior theory,and the adaptive histogram equalization algorithm was used to limit the contrast to process the smoothed image to restore the chromatic aberration caused by the fog.Accurate atmospheric light value was selected.The Brenner clear evaluation standard was introduced to adaptively determine the tolerance value to realize the correction of the transmittance.The foggy image and the clear image were weighted and merged to save more details of the image.In the YUV color space,the brightness component Y was adjusted to improve the image brightness.Experimental results show that it can effectively improve the problem of high brightness and low definition of foggy images.Compared with other algorithms,the image details are relatively more complete and the overall image defogging effect is better.

关 键 词：暗通道 引导滤波 自适应容差 调整亮度 颜色空间 图像融合 限制对比度自适应直方图均衡化算法 

分 类 号：TP317.4[自动化与计算机技术—计算机软件与理论]