基于高低频特征增强和透射率修正的复杂图像去雾方法  

Defogging Method of Complex Images Based on High and Low Frequency Feature Enhancement and Transmittance Correction

作　　者：王士斌[1] 郭嘉懿 WANG Shibin;GUO Jiayi(College of Computer and Information Engineering,Henan Normal University,Xinxiang 453000,Henan Province,China)

机构地区：[1]河南师范大学计算机与信息工程学院,河南新乡453000

出　　处：《吉林大学学报（理学版）》2024年第5期1138-1144,共7页Journal of Jilin University:Science Edition

基　　金：河南省高等学校重点科研项目(批准号:24A520018)。

摘　　要：针对复杂图像中存在非均匀散射介质(如大气湍流、烟雾、雾霾等),导致光线在不同区域的传播和散射特性不同,较难准确恢复图像能见度的问题,提出一种基于高低频特征增强和透射率修正的复杂图像去雾方法.首先,基于奇异值分解和Gamma拐点校正,设计低频特征增强方法;其次,基于Shearlet变换分解和非线性变换,得到高频特征增强方法;再次,利用软抠图精化所估计的透射率,构建透射率修正策略;最后,融合上述3种方法,根据大气光值和精化透射率,完成图像去雾,分别增强高、低频特征后,将两者叠加,获得增强的去雾图像.经去雾图像的视觉感观和客观评价指标结果验证表明,该方法的去雾效果较好,能有效恢复复杂图像的细节信息,改善图像的整体视觉质量.Aiming at the problem that there were non-uniform scattering media(such as atmospheric turbulence,smoke,haze,etc.)in complex images,which led to different propagation and scattering characteristics of light in different regions,making it difficult to accurately restore the visibility of the image,we proposed a defogging method of complex image based on high and low frequency feature enhancement and transmittance correction.Firstly,we designed low frequency feature enhancement methods based on singular value decomposition and Gamma inflection point correction.Secondly,based on Shearlet transformation decomposition and nonlinear transformation,we obtained a high frequency feature enhancement method.Thirdly,we used soft cutout to refine the estimated transmittance and constructed a transmittance correction strategy.Finally,by integratin g the above three methods,based on atmospheric light values and refined transmittance,image dehazing was completed.After enhancing high and low frequency features respectively,we superimposed the two to obtain an enhanced dehazing image.The visual perception and objective evaluation indicators of dehazing images have been verified that the proposed method has good dehazing effect and can effectively restore the detailed information of complex images,improving the overall visual quality of the images.

关 键 词：低频特征增强 高频特征增强 透射率估计 透射率精化 复杂图像去雾 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]