基于卷积神经网络的图像去雾算法

陈清江; 张雪; 柴昱洲

doi:10.3788/YJYXS20193402.0220

您当前的位置：

首页 >

文章列表页 >

基于卷积神经网络的图像去雾算法

图像处理 | 更新时间：2020-07-05

- 基于卷积神经网络的图像去雾算法
- Image defogging algorithms based on multiscale convolution neural network
- 液晶与显示 2019年34卷第2期页码：220-227
- 作者机构：
  
  1.西安建筑科技大学理学院, 陕西西安 710055
  2.空间电子信息技术研究院, 陕西西安 710000
- 作者简介：
  
  [ "陈清江(1966-), 男, 河南信阳人, 博士, 教授, 2006年于西安交通大学获博士学位, 主要从事小波分析、图像处理与信号处理方面的研究。E-mail:qjchen66xytu@126.com" ]
  [ "张雪(1995-), 女, 陕西宝鸡人, 硕士研究生, 2017年于商洛学院获得理学学士学位, 主要从事小波分析、图像处理与信号处理方面的研究。E-mail:2445161583@qq.com" ]
- 基金信息：
  
  国家自然科学基金(61403298);陕西省自然科学基金(2015JM1024);陕西省教育厅专项科研计划(2013JK0586);陕西省教育厅自然科学基金(15JK2157);National Nature Science Foundation of China(61403298);Natural Science Foundation of Shanxi Province of China(2015JM1024);Special Research Projects of Shaanxi Provincial Department of Education(2013JK0586);Natural Science Foundation of Shaanxi Provincial Department of Education(15JK2157)
- DOI：10.3788/YJYXS20193402.0220
  中图分类号： TP391.4
- 收稿日期：2018-09-17，
  
  录用日期：2018-11-25，
  
  纸质出版日期：2019-02-05
- 稿件说明：
移动端阅览
陈清江, 张雪, 柴昱洲. 基于卷积神经网络的图像去雾算法[J]. 液晶与显示, 2019,34(2):220-227.

Qing-jiang CHEN, xue ZHANG, yu-zhou CHAI. Image defogging algorithms based on multiscale convolution neural network[J]. Chinese journal of liquid crystals and displays, 2019, 34(2): 220-227.
陈清江, 张雪, 柴昱洲. 基于卷积神经网络的图像去雾算法[J]. 液晶与显示, 2019,34(2):220-227. DOI： 10.3788/YJYXS20193402.0220.

Qing-jiang CHEN, xue ZHANG, yu-zhou CHAI. Image defogging algorithms based on multiscale convolution neural network[J]. Chinese journal of liquid crystals and displays, 2019, 34(2): 220-227. DOI： 10.3788/YJYXS20193402.0220.

摘要

针对传统的基于先验知识与假设条件的去雾算法在实际应用中受到太多限制的问题，本文提出了一种基于端到端卷积神经网络的去雾算法，即通过学习雾天图像与清晰图像之间的映射关系实现图像去雾。首先，该算法采用了多尺度映射，通过多尺度的卷积提取出雾霾图像的较多细节信息特征；其次，运用反卷积以减少训练网络的复杂性；最后，结合浅层与深层的合并机制将删除特征图中的伪像素，提高恢复无雾图像的质量。实验结果表明，本文提出的去雾算法在自然雾天图像和合成雾天图像上均优于其它对比算法，并且合成雾天图像在结构相似度（SSIM）和峰值信噪比（PSNR）两个重要的图像评价指标上都取得了良好的表现。

Abstract

Aiming at the problem that the traditional fogging algorithm

which is mostly based on prior knowledge and hypothesis can hardly be satisfied in practice

a kind of end-to-end convolutional neural network is proposed

by learning the mapping relationship between foggy images and clear images

image defogging can be realized directly. First

the algorithm is adopted by multi-scale mapping. Through multiscale convolution

it can extract haze features with more detailed information. Secondly

deconvolution is used to reduce the complexity of computer training network. Finally

Combining the the parallel algorithm of shallow layer and deep layer

the pseudo-pixels in the feature map will be deleted so as to improve the quality of image restoration without fog. The experimental results show that the proposed algorithm is superior to other algorithms in both natural fog images and composite fog images

and the composite fog images have achieved good performance on two important image evaluation indexes of SSIM and PSNR.

关键词

Keywords

references

FAN T H, LI C L, MA X, et al. An improved single image defogging method based on retinex[C]// Proceedings of the 2017 2 nd International Conference on Image, Vision and Computing . Chengdu, China: IEEE, 2017: 410-413.

KIM J Y, KIM L S, HWANG S H. An Advanced Contrast Enhancement Using Partially Overlapped Sub-Block Histogram Equalization [M]. Piscataway, NJ, USA:IEEE Press, 2001.

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

FATTAL R. Single image dehazing[J]. ACM Transactions on Graphics , 2008, 27(3):72.

HE K M, SUN J, TANG X O. Single image haze removal using dark channel prior[C]// Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition . Miami, FL, USA: IEEE, 2009: 1956-1963.

MENG G F, WANG Y, DUAN J Y, et al . Efficient image dehazing with boundary constraint and contextual regularization[C]// Proceedings of 2013 IEEE International Conference on Computer Vision . Sydney, NSW, Australia: IEEE, 2013: 617-624.

LI Z W, TAN P, TAN R T, et al . Simultaneous video defogging and stereo reconstruction[C]// Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition . Boston, MA, USA: IEEE, 2015: 4988-4997.

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.

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

刘海波, 杨杰, 吴正平, 等.改进的基于雾气理论的视频去雾[J].光学精密工程, 2016, 24(7):1789-1798.

LIU H B, YANG J, WU Z P, et al . Improved video defogging based on fog theory[J]. Optics and Precision Engineering , 2016, 24(7):1789-1798. (in Chinese)

代书博, 徐伟, 朴永杰, 等.基于暗原色先验的遥感图像去雾方法[J].光学学报, 2017, 37(3):0328002.

DAI S B, XU W, PIAO Y J, et al . Remote sensing image defogging based on dark channel prior[J]. Acta Optica Sinica , 2017, 37(3):0328002. (in Chinese)

COX L J. Optics of the atmosphere-scattering by molecules and particles[J]. Optica Acta:International Journal of Optics , 1977, 24(7):779.

MCCARTNEY E J. Optics of the Atmosphere : Scattering By Molecules and Particles [M]. New York: John Wiley and Sons, Inc., 1976: 1.

NARASIMHAN S G, NAYAR S K. Contrast restoration of weather degraded images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2003, 25(6):713-724.

WANG Z, BOVIK A C, SHEIKH H R, et al . Image quality assessment:from error visibility to structural similarity[J]. IEEE Transactions on Image Processing , 2004, 13(4):600-612.

MANNOS J, SAKRISON D. The effects of a visual fidelity criterion of the encoding of images[J]. IEEE Transactions on Information Theory , 1974, 20(4):525-536.

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

用于眼底视网膜图像的去雾状杂散光算法

基于FPGA的Winograd算法卷积神经网络加速器设计与实现

基于明亮区域分割的图像去雾算法

基于代价敏感正则化和EfficientNet的糖尿病视网膜病变分类方法

双任务卷积神经网络的图像去模糊方法