基于超像素图像分割的暗通道先验去雾改进算法

金天虎; 陶砚蕴; 李佐勇

doi:10.12263/DZXB.20211566

您当前的位置：

首页 >

文章列表页 >

基于超像素图像分割的暗通道先验去雾改进算法

学术论文 | 更新时间：2025-07-02

- 基于超像素图像分割的暗通道先验去雾改进算法
- An Improved Dark Channel Prior Dehazing Algorithm Based on Superpixel Image Segmentation
- 电子学报 2023年51卷第1期页码：146-159
- 作者机构：
  
  1.苏州大学轨道交通学院，江苏苏州 215137
  2.福建省信息处理与智能控制重点实验室（闽江学院），福建闽江 350108
  3.南京大学计算机软件新技术国家重点实验室，江苏南京 215311
- 作者简介：
  
  [ "金天虎男，苏州大学轨道交通学院硕士研究生.主要研究方向为图像处理、图像去雾、目标检测.E-mail: 20204246023@stu.suda.edu.cn" ]
  [ "陶砚蕴（通讯作者）男，华东理工大学控制科学与工程博士、上海交通大学计算机博士后.苏州大学轨道交通学院副教授.主要研究方向为计算智能、机器学习、生物医学工程.目前发表SCI论文15篇，主持国家级项目2项、省级项目1项、国家重点实验室开放课题1项、省级重点实验室开放课题2项." ]
  李佐勇男，本硕博先后就读福州大学、南京理工大学，访学香港理工大学，美国北卡罗来纳大学.闽江学院科研处副处长，计算机与控制工程学院教授，福建省信息处理与智能控制重点实验室主任，福建省雏鹰计划青年拔尖人才，福建省百千万人才，福州市闽都英才青年拔尖人才，福州大学、福建农林大学、山东科技大学，福建工程学院、温州大学硕士生导师，主要研究方向为模式识别、机器学习、深度学习在医学和工业等.E-mail: fzulzytdq@126.com
- 基金信息：
  
  福建省信息处理与智能控制重点实验室（闽江学院）开放课题(MJUKF-IPIC202104);计算机软件新技术国家重点实验室（南京大学）开放课题(KFKT2021B40)
- DOI：10.12263/DZXB.20211566
  中图分类号： TP391;
- 收稿：2021-11-22，
  
  修回：2022-02-20，
  
  纸质出版：2023-01-25
- 稿件说明：
移动端阅览
金天虎,陶砚蕴,李佐勇.基于超像素图像分割的暗通道先验去雾改进算法[J].电子学报,2023,51(01):146-159.

JIN Tian-hu,TAO Yan-yun,LI Zuo-yong.An Improved Dark Channel Prior Dehazing Algorithm Based on Superpixel Image Segmentation[J].ACTA ELECTRONICA SINICA,2023,51(01):146-159.
金天虎,陶砚蕴,李佐勇.基于超像素图像分割的暗通道先验去雾改进算法[J].电子学报,2023,51(01):146-159. DOI： 10.12263/DZXB.20211566.

JIN Tian-hu,TAO Yan-yun,LI Zuo-yong.An Improved Dark Channel Prior Dehazing Algorithm Based on Superpixel Image Segmentation[J].ACTA ELECTRONICA SINICA,2023,51(01):146-159. DOI： 10.12263/DZXB.20211566.

摘要

本文针对暗通道先验去雾算法在天空等明亮区域存在明显的噪声放大和色彩失真的问题，从大气散射模型和暗通道先验理论出发修正大气光值和非暗通道区域透射率，提出了基于超像素图像分割的暗通道先验去雾改进算法.本文算法基于大气散射模型和暗通道先验理论建立雾天成像模型；通过超像素阈值分割算法将图像分为暗通道区域和非暗通道区域，暗通道区域（Dark Channel Region，DCR）即图像中符合暗通道先验理论的部分，非暗通道区域（Non-Dark Channel Region，NDCR）即图像中不符合暗通道先验理论的部分；再分别通过非暗通道区域和暗通道区域的超像素，估计全局大气光值，修正非暗通道区域透射率；最终根据大气散射模型恢复无雾图像.本文算法提高了全局大气光值的准确性，有效抑制了天空等非暗通道区域的失真，复原图像更加清晰自然，增强了视觉效果.主观和客观评价的实验表明，本文算法能够取得比传统算法更优的去雾效果.

Abstract

In view of the obvious noise amplification and color distortion of dark channel prior defogging algorithm in bright areas such as sky

this paper proposes an improved dark channel prior defogging algorithm based on superpixel image segmentation. Based on the atmospheric scattering model and dark channel prior theory

the atmospheric light value and the transmittance of non-dark channel region are modified. Firstly

a foggy imaging model is established based on atmospheric scattering model and dark channel prior theory. Then

the image is divided into dark channel region and non-dark channel region through the super pixel threshold segmentation algorithm. Dark channel region (DCR) is the part of the image conforming to the dark channel prior theory. Non-dark channel region (NDCR) is the part of the image that does not conform to the dark channel prior theory. Then the global atmospheric light value is estimated by the superpixels of the non-dark channel region and the dark channel region

respectively

and then the transmittance of the non-dark channel region is corrected. Finally

the fog-free image is restored according to the atmospheric scattering model. The algorithm in this paper improves the accuracy of global atmospheric light values

and effectively inhibits the distortion of sky and other non-dark channel regions

making the restored image clearer and more natural

and also enhances the visual effect. Subjective and objective evaluation experiments show that the proposed algorithm can achieve better defogging effect than the traditional algorithm.

关键词

Keywords

references

NAYAR S K , NARASIMHAN S G . Vision in bad weather [C]// Proceedings of the Seventh IEEE International Conference on Computer Vision . Kerkyra : IEEE , 1999 : 820 - 827 .

NARASIMHAN S G , NAYAR S K . Chromatic framework for vision in bad weather [C]// Proceedings IEEE Conference on Computer Vision and Pattern Recognition(CVPR 2000) . Hilton Head : IEEE , 2000 : 598 - 605 .

SHEHATA M S , CAI J , BADAWY W M , et al . Video-based automatic incident detection for smart roads: The outdoor environmental challenges regarding false alarms [J]. IEEE Transactions on Intelligent Transportation Systems , 2008 , 9 ( 2 ): 349 - 360 .

BRONTE S , BERGASA L M , ALCANTARILLA P F . Fog detection system based on computer vision techniques [C]// 2009 12th International IEEE Conference on Intelligent Transportation Systems . St . Louis : IEEE , 2009 : 1 - 6 .

JIA Z , WANG H C , CABALLERO R E , et al . A two-step approach to see-through bad weather for surveillance video quality enhancement [J]. Machine Vision and Applications , 2012 , 23 ( 6 ): 1059 - 1082 .

WANG W C , YUAN X H . Recent advances in image dehazing [J]. IEEE/CAA Journal of Automatica Sinica , 2017 , 4 ( 3 ): 410 - 436 .

谢皓 , 张健 , 倪江群 . 数字图像操作取证综述 [J]. 信号处理 , 2021 , 37 ( 12 ): 2323 - 2337 .

XIE Hao , ZHANG Jian , NI Jiangqun . A Survey of Digital Image Operation Forensics [J]. JOURNAL OF SIGNAL PROCESSING , 2021 , 37 ( 12 ): 2323 - 2337 . (in Chinese) .

TAN R T . Visibility in bad weather from a single image [C]// 2008 IEEE Conference on Computer Vision and Pattern Recognition . Anchorage : IEEE , 2008 : 1 - 8 .

FATTAL R . Single image dehazing [J]. ACM Transactions on Graphics , 2008 , 27 ( 3 ): 1 - 9 .

ZHU Q S , MAI J M , SHAO L . A fast single image haze removal algorithm using color attenuation prior [J]. IEEE Transactions on Image Processing , 2015 , 24 ( 11 ): 3522 - 3533 .

HE K M , SUN J , TANG X O . Single image haze removal using dark channel prior [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2011 , 33 ( 12 ): 2341 - 2353 .

HE K M , SUN J , TANG X O . Guided image filtering [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2013 , 35 ( 6 ): 1397 - 1409 .

WANG G Y , REN G H , JIANG L H , et al . Single image dehazing algorithm based on sky region segmentation [J]. Information Technology Journal , 2013 , 12 ( 6 ): 1168 - 1175 .

蒋建国 , 侯天峰 , 齐美彬 . 改进的基于暗原色先验的图像去雾算法 [J]. 电路与系统学报 , 2011 , 16 ( 2 ): 7 - 12 .

JIANG J G , HOU T F , QI M B . Improved algorithm on image haze removal using dark channel prior [J]. Journal of Circuits and Systems , 2011 , 16 ( 2 ): 7 - 12 . (in Chinese) .

ZHU Y B , LIU J M , HAO Y G . An single image dehazing algorithm using sky detection and segmentation [J]. 2014 7th International Congress on Image and Signal Processing , 2014 : 248 - 252 .

肖进胜 , 高威 , 邹白昱 , 等 . 基于天空约束暗通道先验的图像去雾 [J]. 电子学报 , 2017 , 45 ( 2 ): 346 - 352 .

XIAO J S , GAO W , ZOU B Y , et al . Image dehazing based on sky-constrained dark channel prior [J]. Acta Electronica Sinica , 2017 , 45 ( 2 ): 346 - 352 . (in Chinese) .

HASSAN H , BASHIR A K , AHMAD M , et al . Real-time image dehazing by superpixels segmentation and guidance filter [J]. Journal of Real-Time Image Processing , 2021 , 18 ( 5 ): 1555 - 1575 .

KIM S E , PARK T H , EOM I K . Fast single image dehazing using saturation based transmission map estimation [J]. IEEE Transactions on Image Processing , 2020 , 29 : 1985 - 1998 .

ACHANTA R , SHAJI A , SMITH K , et al . SLIC superpixels compared to state-of-the-art superpixel methods [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2012 , 34 ( 11 ): 2274 - 2282 .

MCCARTNEY E J , HALL F F . Optics of the atmosphere: Scattering by molecules and particles [J]. Physics Today , 1977 , 30 ( 5 ): 76 - 77 .

HAN X X , FENG H W , BU Q R , et al . Image dehazing base on two-peak channel prior [C]// 2016 IEEE International Conference on Image Processing . Phoenix : IEEE , 2016 : 2236 - 2240 .

XU Y S , GUO X Q , WANG H Y , et al . Single image haze removal using light and dark channel prior [C]// 2016 IEEE/CIC International Conference on Communications in China(ICCC) . Chengdu : IEEE , 2016 : 1 - 6 .

LI B Y , REN W Q , FU D P , et al . Benchmarking single-image dehazing and beyond [J]. IEEE Transactions on Image Processing , 2019 , 28 ( 1 ): 492 - 505 .

SARA U , AKTER M , UDDIN M S . Image quality assessment through FSIM, SSIM, MSE and PSNR—A comparative study [J]. Journal of Computer and Communications , 2019 , 7 ( 3 ): 8 - 18 .

FAN D , GUO X Y , LU X , et al . Image defogging algorithm based on sparse representation [J]. Complexity , 2020 , 2020 : 6835367 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于梯度引导偏振度估算的图像去雾

基于跨层注意力特征交互和多尺度通道注意力的单幅图像去雾网络

基于双判别器异构CycleGAN框架下多阶通道注意力校准的室外图像去雾