Research on single image haze removal algorithm based on parameter optimization search of linear model

Yi-tao Liang, Kui-bin Zhao, Wenqiang Zhang, Yafei Li
{"title":"Research on single image haze removal algorithm based on parameter optimization search of linear model","authors":"Yi-tao Liang, Kui-bin Zhao, Wenqiang Zhang, Yafei Li","doi":"10.1109/ICAMECHS.2018.8507148","DOIUrl":null,"url":null,"abstract":"Image defogging method based on non physical model (the image contrast enhancement method) and image dehazing method based on physical model (the atmospheric scattering model method), it is the two kinds of method that is focused on at present. The innovation of this article is: the estimation value of parameter achieved by atmospheric scattering model image dehazing method is not optimal; and the method of contrast enhancement makes the part of clear image and the depth of information distortion. On the basis of the theoretical analysis this paper gives an improved linear model which is proposed to describe the fog removal principle based on the atmospheric scattering model and the contrast enhancement method, and the fog removal problems of models were converted into the optimization searching in parameter space. Initial estimates parameters of atmospheric scattering model method based on linear model in the aspect of solving the problem, and the genetic algorithm and the clarity decision function are introduced to optimize the parameters. And then obtain defogging image. Experimental results demonstrate that the proposed method can achieve a better dehazing effect and applicability compared to some state-of-the-art methods.","PeriodicalId":325361,"journal":{"name":"2018 International Conference on Advanced Mechatronic Systems (ICAMechS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 International Conference on Advanced Mechatronic Systems (ICAMechS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAMECHS.2018.8507148","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

Abstract

Image defogging method based on non physical model (the image contrast enhancement method) and image dehazing method based on physical model (the atmospheric scattering model method), it is the two kinds of method that is focused on at present. The innovation of this article is: the estimation value of parameter achieved by atmospheric scattering model image dehazing method is not optimal; and the method of contrast enhancement makes the part of clear image and the depth of information distortion. On the basis of the theoretical analysis this paper gives an improved linear model which is proposed to describe the fog removal principle based on the atmospheric scattering model and the contrast enhancement method, and the fog removal problems of models were converted into the optimization searching in parameter space. Initial estimates parameters of atmospheric scattering model method based on linear model in the aspect of solving the problem, and the genetic algorithm and the clarity decision function are introduced to optimize the parameters. And then obtain defogging image. Experimental results demonstrate that the proposed method can achieve a better dehazing effect and applicability compared to some state-of-the-art methods.
基于线性模型参数优化搜索的单幅图像去雾算法研究
基于非物理模型的图像去雾方法(图像对比度增强方法)和基于物理模型的图像去雾方法(大气散射模型方法),是目前比较关注的两种方法。本文的创新之处在于:大气散射模型图像去雾方法得到的参数估计值并非最优;而对比度增强的方法使得部分清晰的图像和深度的信息失真。在理论分析的基础上,提出了一种基于大气散射模型和对比度增强方法的改进线性模型来描述消雾原理,并将模型的消雾问题转化为参数空间的优化搜索问题。在求解问题方面,提出了基于线性模型的大气散射模型参数初始估计方法,并引入遗传算法和清晰度决策函数对参数进行优化。然后得到去雾图像。实验结果表明,与现有的除雾方法相比,该方法具有更好的除雾效果和适用性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信