首页 > 论文 > 光学学报 > 38卷 > 3期(pp:310001--1)

基于稀疏特征提取的单幅图像去雾

Single Image Dehazing Based on Sparse Feature Extraction

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

摘要

为解决暗通道先验去雾算法在天空区域和大片白色区域色彩失真的问题, 提出了一种基于稀疏表示模型和特征提取的单幅图像去雾算法。通过稀疏字典的训练过程, 学习雾天图像的稀疏特征, 初步优化粗略介质传输图的稀疏系数。根据雾天灰度图像的稀疏特征, 进一步精细化介质传输图。逆向求解雾天退化模型, 得到去雾图像。实验结果表明, 所提算法在天空区域的处理上优势明显, 同时恢复出更多的图像细节和边缘信息。

Abstract

To overcome the color distortion in sky regions and large white regions brought by the dark channel prior dehazing algorithm, we propose a single image dehazing algorithm based on sparse representation model and feature extraction. Firstly, the algorithm learns the sparse features of foggy images via training sparse dictionary, and optimizes the sparse coefficients of the rough medium transmission image preliminarily. Then, the algorithm refines the medium transmission image by the sparse features of foggy gray images. Finally, with the converse solution of the degradation model, the algorithm obtains the dehazing image. The experimental results demonstrate that the proposed algorithm has obvious advantages in the processing of the sky area, and at the same time, it can recover more image details and marginal information.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TN911.73;TP391

DOI:10.3788/aos201838.0310001

所属栏目:图像处理

基金项目:国家自然科学基金(61372167, 61701524, 61773397)

收稿日期:2017-09-12

修改稿日期:2017-11-02

网络出版日期:--

作者单位    点击查看

刘坤:空军工程大学航空航天工程学院, 陕西 西安 710038
毕笃彦:空军工程大学航空航天工程学院, 陕西 西安 710038
王世平:空军工程大学航空航天工程学院, 陕西 西安 710038
何林远:空军工程大学航空航天工程学院, 陕西 西安 710038
高山:空军工程大学航空航天工程学院, 陕西 西安 710038

联系人作者:何林远(hal1983@163.com)

备注:刘坤(1994-),男,硕士研究生,主要从事图像增强方面的研究。E-mail: 15353587039@163.com

【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】Liang J, Ju H J, Zhang W F, et al. Review of optical polarimetric dehazing technique[J]. Acta Optica Sinica, 2017, 37(4): 0400001.
梁健, 巨海娟, 张文飞, 等. 偏振光学成像去雾技术综述[J]. 光学学报, 2017, 37(4): 0400001.

【3】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.
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.

【4】Tan R T. Visibility in bad weather from a single image[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2008: 10139948.

【5】Fattal R. Single image dehazing[J]. ACM Transactions on Graphics, 2008, 27(3): 721-728.

【6】Dong X M, Hu X Y, Peng S L, et al. Single color image dehazing using sparse priors[C]. 17th IEEE International Conference on Image Processing, 2010, 119(5) : 3593-3596.

【7】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.

【8】He K M, Sun J, Tang X O, et al. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341-2353.

【9】He K M, Sun J, Tang X O, et al. Guided image filtering[C]. 11th European Conference on Computer Vision, 2010: 1-14.

【10】Li J Y, Hu Q W, Ai M Y, et al. Image haze removal based on sky region detection and dark channel prior[J]. Journal of Image and Graphics, 2015, 20(4): 514-519.
李加元, 胡庆武, 艾明耀, 等. 结合天空识别和暗通道原理的图像去雾[J]. 中国图象图形学报, 2015, 20(4): 514-519.

【11】Bi D Y, Sui P, He L Y, et al. Higher-order Markov random fields defogging based on Color Lines[J]. Journal of Electronics & Information Technology, 2016, 38(9): 2405-2409.
毕笃彦, 眭萍, 何林远, 等. 基于Color Lines先验的高阶马尔科夫随机场去雾[J]. 电子与信息学报, 2016, 38(9): 2405-2409.

【12】Yang J C, Wright J, Huang T, et al. Image super-resolution as sparse representation of raw image patches[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2008: 1-8.

【13】Zhang K, Zhang L, Yang M H. Fast compressive tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(10): 2002-2015.

【14】Zhang S P, Yao H X, Sun X, et al. Sparse coding based visual tracking: review and experimental comparison[J]. IEEE Transactions on Pattern Recognition, 2013, 46(7): 1772-1788.

【15】Yin W, Li Y X, Zhou Z M, et al. Remote sensing image fusion based on sparse representation[J]. Acta Optica Sinica, 2013, 33(4): 0428003.
尹雯, 李元祥, 周则明, 等. 基于稀疏表示的遥感图像融合方法[J]. 光学学报, 2013, 33(4): 0428003.

【16】Nan D, Bi D Y, Ma S P, et al. Single image dehazing method based on scene depth constraint[J]. Acta Electronica Sinica, 2015, 43(3): 500-504.
南栋, 毕笃彦, 马时平, 等. 基于景深约束的单幅雾天图像去雾算法[J]. 电子学报, 2015, 43(3): 500-504.

【17】Pati Y C, Rezaiifar R, Krishnaprasad P S. Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition[C]. 27th Asilomar Conference on Signals, Systems and Computers, 1993: 4846193.

【18】Xu L, Zheng S C, Jia J Y. Unnatural L0 sparse representation for natural image deblurring[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2013: 1107-1114.

【19】Chen C, Do M N, Wang J. Robust image and video dehazing with visual artifact suppression via gradient residual minimization[M]. Berlin: Springer, 2016: 576-591.

【20】Ren W Q, Liu S, Zhang H, et al. Single image dehazing via multi-scale convolutional neural networks[M]. Cham: Springer International Publishing, 2016: 154-169.

【21】Gao Y, Yun L J, Shi J S, et al. Enhancement dark channel algorithm of fog image based on the TV model[J]. Chinese Journal of Lasers, 2015, 42(8): 0809001.
高银, 云利军, 石俊生, 等. 基于TV模型的暗原色理论雾天图像复原算法[J]. 中国激光, 2015, 42(8): 0809001.

引用该论文

Liu Kun,Bi Duyan,Wang Shiping,He Linyuan,Gao Shan. Single Image Dehazing Based on Sparse Feature Extraction[J]. Acta Optica Sinica, 2018, 38(3): 0310001

刘坤,毕笃彦,王世平,何林远,高山. 基于稀疏特征提取的单幅图像去雾[J]. 光学学报, 2018, 38(3): 0310001

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