首页 > 论文 > 光学学报 > 40卷 > 2期(pp:0210003--1)

基于双域分解的多尺度深度学习单幅图像去雾

Single Image Dehazing of Multiscale Deep-Learning Based on Dual-Domain Decomposition

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对传统单幅图像去雾算法容易受到雾图先验信息制约而导致颜色失真,以及现有深度学习去雾算法受网络模型限制而存在去雾残留等问题,提出了一种基于双域分解的多尺度深度学习单幅图像去雾方法,设计了一个包含低频去雾子网和高频去雾子网的多尺度深度学习网络模型。首先采用双边滤波器对有雾图像进行分解,得到雾图的高、低频子图,然后通过设计的网络模型分别学习雾图高、低频子图与高、低频透射率之间的映射关系,再将模型学习得到的高、低频透射率进行融合,得到原始雾图对应的场景透射率图,最后根据大气散射模型实现有雾图像到无雾图像的恢复,采用雾图数据集对该模型进行训练测试。结果表明,所提方法在合成有雾图像和真实自然雾图的实验中均能取得良好的去雾效果,在主观评价和客观评价方面均优于其他对比算法。

Abstract

The traditional single image dehazing algorithms are susceptible to the prior information of hazy images, resulting in color distortion. Furthermore, the deep-learning dehazing algorithms are limited by the network model, leading to residual haze. To overcome these problems, this study proposes a single image dehazing method of multiscale deep-learning based on dual-domain decomposition. This method develops a multiscale deep-learning network model that includes low- and high-frequency dehazing subnets. Firstly, the hazy image is decomposed using bilateral filters to obtain high- and low-frequency sub-images of the hazy image. Subsequently, the mapping relations between the high- and low-frequency sub-images as well as the high- and low-frequency transmissivity of the hazy image are learned using the developed network model. The high- and low-frequency transmissivity obtained by model learning is fused to obtain the scene transmissivity of the original hazy image. Finally, the hazy image is restored to the dehazed image based on the atmospheric scattering model, which is trained and tested using the hazy image dataset. The experimental results denote that the proposed method can achieve a good dehazing effect for the synthetic hazy images and real natural hazy images and that it is superior to other contrast algorithms in subjective and objective evaluations.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.4

DOI:10.3788/AOS202040.0210003

所属栏目:图像处理

基金项目:国家自然科学基金、长江学者和创新团队发展计划、教育部人文社会科学研究基金;

收稿日期:2019-08-08

修改稿日期:2019-09-23

网络出版日期:2020-02-01

作者单位    点击查看

陈永:兰州交通大学电子与信息工程学院, 甘肃 兰州 730070
郭红光:兰州交通大学电子与信息工程学院, 甘肃 兰州 730070
艾亚鹏:兰州交通大学电子与信息工程学院, 甘肃 兰州 730070

联系人作者:陈永(edukeylab@126.com)

备注:国家自然科学基金、长江学者和创新团队发展计划、教育部人文社会科学研究基金;

【1】Wu D, Zhu Q S. The latest research progress of image dehazing [J]. Acta Automatica Sinica. 2015, 41(2): 221-239.
吴迪, 朱青松. 图像去雾的最新研究进展 [J]. 自动化学报. 2015, 41(2): 221-239.

【2】Xu Y, Wen J, Fei L K, et al. Review of video and image defogging algorithms and related studies on image restoration and enhancement [J]. IEEE Access. 2016, 4: 165-188.

【3】Liu D M, Chang F L. Coarse-to-fine saliency detection based on non-subsampled contourlet transform enhancement [J]. Acta Optica Sinica. 2019, 39(1): 0115003.
刘冬梅, 常发亮. 基于非下采样轮廓小波变换增强的从粗到精的显著性检测 [J]. 光学学报. 2019, 39(1): 0115003.

【4】Zhang S, Tang G J, Liu X H, et al. Retinex based low-light image enhancement using guided filtering and variational framework [J]. Optoelectronics Letters. 2018, 14(2): 156-160.

【5】Dong L L, Ding C, Xu W H. Two improved methods based on histogram equalization for image enhancement [J]. Acta Electronica Sinica. 2018, 46(10): 2367-2375.
董丽丽, 丁畅, 许文海. 基于直方图均衡化图像增强的两种改进方法 [J]. 电子学报. 2018, 46(10): 2367-2375.

【6】He K M, Sun J, Tang X O. Single image haze removal using dark channel prior . [C]∥2009 IEEE Conference on Computer Vision and Pattern Recognition, June 20-25, 2009, Miami, FL, USA. New York: IEEE. 2009, 1956-1963.

【7】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.

【8】Su C, Bi G L, Jin L X, et al. Dehazing algorithm based on dark-channel image centroid offset [J]. Acta Optica Sinica. 2019, 39(5): 0533001.
苏畅, 毕国玲, 金龙旭, 等. 基于暗通道图像质心偏移量的去雾算法 [J]. 光学学报. 2019, 39(5): 0533001.

【9】Meng G F, Wang Y, Duan J Y, et al. Efficient image dehazing with boundary constraint and contextual regularization . [C]∥2013 IEEE International Conference on Computer Vision, December 1-8, 2013, Sydney, NSW, Australia. New York: IEEE. 2013, 617-624.

【10】Guo H, Xu X T, Li B. Study on image dehazing methods based on dark channel prior [J]. Acta Optica Sinica. 2018, 38(4): 0410002.
郭翰, 徐晓婷, 李博. 基于暗原色先验的图像去雾方法研究 [J]. 光学学报. 2018, 38(4): 0410002.

【11】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.

【12】Ren W Q, Liu S, Zhang H, et al. Single image dehazing via multi-scale convolutional neural networks [M]. ∥Leibe B, Matas J, Sebe N, et al. Computer vision-ECCV 2016. Lecture notes in computer science. Cham: Springer. 2016, 9906: 154-169.

【13】Li B Y, Peng X L, Wang Z Y, et al. AOD-Net: all-in-one dehazing network . [C]∥2017 IEEE International Conference on Computer Vision (ICCV), October 22-29, 2017, Venice, Italy. New York: IEEE. 2017, 4780-4788.

【14】Cox L J. Optics of the atmosphere-scattering by molecules and particles [J]. Optica Acta: International Journal of Optics. 1977, 24(7): 779-788.

【15】LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition [J]. Proceedings of the IEEE. 1998, 86(11): 2278-2324.

【16】Yang A P, Wang H X, Wang J B, et al. Image dehazing based on transmission fusion and multi-guided filtering [J]. Acta Optica Sinica. 2018, 38(12): 1210001.
杨爱萍, 王海新, 王金斌, 等. 基于透射率融合与多重导向滤波的单幅图像去雾 [J]. 光学学报. 2018, 38(12): 1210001.

【17】Knaus C, Zwicker M. Dual-domain image denoising . [C]∥2013 IEEE International Conference on Image Processing, September 15-18, 2013, Melbourne, VIC, Australia. New York: IEEE. 2013, 440-444.

【18】He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition . [C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE. 2016, 770-778.

【19】He K M, Zhang X Y, Ren S Q, et al. Delving deep into rectifiers: surpassing human-level performance on ImageNet classification . [C]∥2015 IEEE International Conference on Computer Vision (ICCV), December 7-13, 2015, Santiago, Chile. New York: IEEE. 2015, 1026-1034.

【20】Li B Y, Ren W Q, Fu D P, et al. -04-22) [2019-08-07] . https:∥arxiv.org/abs/1712.04143v1. 2019.

引用该论文

Chen Yong,Guo Hongguang,Ai Yapeng. Single Image Dehazing of Multiscale Deep-Learning Based on Dual-Domain Decomposition[J]. Acta Optica Sinica, 2020, 40(2): 0210003

陈永,郭红光,艾亚鹏. 基于双域分解的多尺度深度学习单幅图像去雾[J]. 光学学报, 2020, 40(2): 0210003

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF