基于补偿透射率和自适应雾浓度系数的图像复原算法

杨燕; 王志伟

doi:10.11959/j.issn.1000-436x.2020009

您当前的位置：

首页 >

文章列表页 >

基于补偿透射率和自适应雾浓度系数的图像复原算法

学术论文 | 更新时间：2024-06-05

- 基于补偿透射率和自适应雾浓度系数的图像复原算法
- Image restoration algorithm based on compensated transmission and adaptive haze concentration coefficient
- 通信学报 2020年41卷第1期页码：66-75
- 作者机构：
  
  兰州交通大学电子与信息工程学院，甘肃兰州 730070
- 作者简介：
  
  [ "杨燕（1972- ），女，河南临颍人，博士，兰州交通大学教授、硕士生导师，主要研究方向为数字图像处理、智能信息处理、语音信号处理" ]
  [ "王志伟（1996- ），男，甘肃平凉人，兰州交通大学硕士生，主要研究方向为计算机视觉、数字图像处理" ]
- 基金信息：
  
  国家自然科学基金资助项目(61561030);甘肃省财政厅基本科研业务费基金资助项目(214138);兰州交通大学教改基金资助项目(160012)
- DOI：10.11959/j.issn.1000-436x.2020009
  中图分类号： TP391.41
- 网络出版日期：2020-01，
  
  纸质出版日期：2020-01-25
- 稿件说明：
移动端阅览
杨燕, 王志伟. 基于补偿透射率和自适应雾浓度系数的图像复原算法[J]. 通信学报, 2020,41(1):66-75.

Yan YANG, Zhiwei WANG. Image restoration algorithm based on compensated transmission and adaptive haze concentration coefficient[J]. Journal on communications, 2020, 41(1): 66-75.
杨燕, 王志伟. 基于补偿透射率和自适应雾浓度系数的图像复原算法[J]. 通信学报, 2020,41(1):66-75. DOI： 10.11959/j.issn.1000-436x.2020009.

Yan YANG, Zhiwei WANG. Image restoration algorithm based on compensated transmission and adaptive haze concentration coefficient[J]. Journal on communications, 2020, 41(1): 66-75. DOI： 10.11959/j.issn.1000-436x.2020009.

摘要

针对传统暗通道先验易在高亮度区域失真和产生光晕效应的不足，提出一种基于补偿透射率和自适应雾浓度系数的雾天图像复原算法。首先利用高斯函数拟合有雾和无雾图像间的衰减关系，通过修正透射率对高亮区域进行补偿。然后分析雾气特性，提出亮度熵概念，对原图亮通道进行逐像素处理求取熵值，结合高斯金字塔提取纹理特征，得到雾气分布图；同时建立一种线性变换来自适应求取雾浓度系数，并获得优化透射率。最后改进局部大气光的获取方法，结合大气散射模型得到复原结果。实验表明，所提算法可以有效复原出降质图像的颜色与细节，明亮度适宜，去雾程度彻底，效果清晰自然。

Abstract

Aiming at the drawbacks of traditional dark channel prior

which was prone to distortion and Halo effects in the bright areas

a haze image restoration algorithm based on compensated transmission and adaptive haze concentration coefficient was proposed.First of all

a Gaussian function was used to fit the attenuation relationship between the haze and haze-free image

and the compensation transmission was set to correct the initial transmission.Then the characteristics of haze was analyzed

the concept of brightness entropy was introduced and the bright channel operation was performed to acquire entropy value with pixel by pixel.Combined with the Gaussian pyramid to extract texture features

the haze distribution map was obtained.An adaptive transformation was established to seek the haze concentration coefficient and get the accurate transmission.Finally

the recovery results were restored by improved atmospheric light value and atmospheric scattering model.Experimental results show that the recovered image has better color and detail

the degree of dehazing is thorough

the brightness is appropriate

and the effect is clear and natural.

关键词

Keywords

references

AL-SAMMARAIE M F , . Contrast enhancement of roads images with foggy scenes based on histogram equalization [C ] // International Conference on Computer Science ＆ Education(ICCSE) . 2015 : 95 - 101 .

YAO L , LIN Y , MUHAMMAD S . An improved multi-scale image enhancement method based on retinex theory [J ] . Journal of Medical Imaging ＆ Health Informatics , 2018 , 8 ( 1 ): 122 - 126 .

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

HE K M , JIAN S , 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 .

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 .

MENG G F , WANG Y , DUAN J Y , et al . Efficient image dehazing with boundary constraint and contextual regularization [C ] // The IEEE International Conference on Computer Vision (ICCV) . 2013 : 617 - 624 .

CAI B L , XU X M , JIA K , et al . DehazeNet:an end-to-end system for single image haze removal [J ] . IEEE Transactions on Image Processing , 2016 , 25 ( 11 ): 5187 - 5198 .

REN W Q , LIU S , ZHANG H , et al . Single image dehazing via multi-scale convolutional neural networks [C ] // European Conference on Computer Vision (ECCV) , 2016 : 154 - 169 .

LIU R , FAN X , HOU M , et al . Learning aggregated transmission propagation networks for haze removal and beyond [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2019 , 30 ( 10 ): 2973 - 2986 .

杨燕 , 陈高科 . 基于光补偿和逐像素透射率的图像复原算法 [J ] . 通信学报 , 2017 , 38 ( 5 ): 48 - 56 .

YANG Y , CHEN G K . Single image visibility restoration using optical compensation and pixel-by-pixel transmission estimation [J ] . Journal on Communications , 2017 , 38 ( 5 ): 48 - 56 .

郭璠 , 唐琎 , 蔡自兴 . 基于融合策略的单幅图像去雾算法 [J ] . 通信学报 , 2014 , 35 ( 7 ): 199 - 207 .

GUO F , TANG J , CAI Z X . Single image defogging based on fusion strategy [J ] . Journal on Communications , 2014 , 35 ( 7 ): 199 - 207 .

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 .

YU T , RIAZ I , PIAO J C , et al . Real-time single image dehazing using block-to-pixel interpolation and adaptive dark channel prior [J ] . IET Image Processing , 2015 , 9 ( 9 ): 725 - 734 .

LI S T , HAO Q B , KANG X D , et al . Gaussian pyramid based multiscale feature fusion for hyperspectral image classification [J ] . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2018 , 11 ( 9 ): 3312 - 3324 .

SUN W , WANG H , SUN C , et al . Fast single image haze removal via local atmospheric light veil estimation [J ] . Computers ＆ Electrical Engineering , 2015 , 46 ( C ): 371 - 378 .

ANCUTI C , ANCUTI C O , VLEESCHOUWER C D . D-HAZY:a dataset to evaluate quantitatively dehazing algorithms [C ] // IEEE International Conference on Image Processing(ICIP) . 2016 : 2226 - 2230 .

HAUTIERE N , TAREL J P , Aubert D , et al . Blind contrast enhancement assessment by gradient ratioing at visible edges [J ] . Image Analysis ＆ Stereology , 2011 , 27 ( 2 ): 87 - 95 .

杨红 , 崔艳 . 基于开运算暗通道和优化边界约束的图像去雾算法 [J ] . 光子学报 , 2018 , 47 ( 6 ): 244 - 250 .

YANG H , CUI Y . Image defogging algorithm based on opening dark channel and improved boundary constraint [J ] . Acta Photonica Sinica , 2018 , 47 ( 6 ): 244 - 250 .

杨燕 , 陈高科 , 周杰 . 基于高斯权重衰减的迭代优化去雾算法 [J ] . 自动化学报 , 2019 , 45 ( 4 ): 819 - 828 .

YANG Y , CHEN G K , ZHOU J . Iterative optimization defogging algorithm using gaussian weight decay [J ] . Acta Automatica Sinica , 2019 , 45 ( 4 ): 819 - 828 .

浏览量

591

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于雾线和颜色衰减先验的图像去雾方法

四通道无监督学习图像去雾网络

基于光补偿和逐像素透射率的图像复原算法

基于误差-参数分析的超分辨率盲辨识和复原算法