低秩与字典表达分解的浓雾霾场景图像去雾算法

黄文君; 李杰; 齐春

doi:10.7652/xjtuxb202004015

您当前的位置：

首页 >

文章列表页 >

低秩与字典表达分解的浓雾霾场景图像去雾算法

更新时间：2025-07-09

- 低秩与字典表达分解的浓雾霾场景图像去雾算法
- A Defogging Algorithm for Dense Fog Images via Low-Rank and Dictionary Expression Decomposition
- 西安交通大学学报 2020年54卷第4期页码：118-125
- 作者机构：
  
  西安交通大学电子与信息学部,西安,710049
- 作者简介：
- 基金信息：
  
  : 2019-09-26。作者简介: 黄文君(1994-),女,硕士生;李杰(通信作者),男,副教授,博士生导师。基金项目: 国家自然科学基金资助项目(61675161,61572395);中央高校基本科研业务费专项资金资助项目(zdyf2017003)
- DOI：10.7652/xjtuxb202004015
  中图分类号： TP391
- 网络首发：2020-04-10，
  
  纸质出版：2020
- 稿件说明：
移动端阅览
黄文君, 李杰, 齐春. 低秩与字典表达分解的浓雾霾场景图像去雾算法[J]. 西安交通大学学报, 2020,54(4):118-125.

A Defogging Algorithm for Dense Fog Images via Low-Rank and Dictionary Expression Decomposition[J]. 2020, 54(4): 118-125.
黄文君, 李杰, 齐春. 低秩与字典表达分解的浓雾霾场景图像去雾算法[J]. 西安交通大学学报, 2020,54(4):118-125. DOI： 10.7652/xjtuxb202004015.

A Defogging Algorithm for Dense Fog Images via Low-Rank and Dictionary Expression Decomposition[J]. 2020, 54(4): 118-125. DOI： 10.7652/xjtuxb202004015.

摘要

针对现有图像去雾算法对浓雾霾场景图像去雾效果不理想的问题

提出了一种低秩与字典表达分解的浓雾霾场景图像去雾算法。首先

根据大气散射物理模型与浓雾霾场景图像中“雾”的全局低秩特性

将退化图像看作低秩“雾”图与相对低秩无雾清晰图像的叠加; 其次

将“雾”图表示为字典矩阵与表达矩阵的乘积

从而通过低秩与字典表达分解模型分解出“雾”图; 再次

利用双三次插值将分解得到的局部“雾”图推广到全局; 最后通过减去“雾”图恢复出无雾的清晰图像。实验结果表明:与现有主流图像去雾算法相比

该算法对浓雾霾场景图像的去雾效果更优

对194幅真实浓雾霾场景图像去雾后

图像平均可见边缘比到达了21.315

平均可见边缘质量因子达到了4.540

图像细节信息得到了较好的恢复。

Abstract

A defogging algorithm for dense fog images based on low-rank and dictionary expression decomposition is proposed to improve the problem that the existing image defogging algorithm is not ideal for image defogging of ha-e scene. Based on the atmospheric scattering physical model and the global low-rank characteristics of -fog- in the ha-e scene image

the degraded image is assumed as a composition of a low-rank -fog- image and an original clear image. Then the -fog- image is expressed as a product of a dictionary matrix and a sparse matrix

so that the -fog- image can be decomposed through the low-rank and dictionary expression decomposition model. The decomposed local -fog- image is extended to a global level by combining the bicubic interpolation. The clear image is finally recovered by subtracting the -fog- image. Experimental results and comparisons with existing mainstream image defogging algorithms on 194 real dense fog images show that the proposed algorithm has bette

关键词

Keywords

references

禹晶, 徐东彬, 廖庆敏. 图像去雾技术研究进展 [J]. 中国图象图形学报, 2011, 16(9): 7-22.

YU Jing, XU Dongbin, LIAO Qingmin. Image defogging: a survey [J]. Journal of Image and Graphics, 2011, 16(9): 7-22.

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): 341-347.

DAI Shubo, XU Wei, PIAO Yongjie, et al. Remote sensing image defogging based on dark channel prior [J]. Acta Optica Sinica, 2017, 37(3): 341-347.

高原原, 胡海苗. 基于多子块协同单尺度Retinex的浓雾图像增强 [J]. 北京航空航天大学学报, 2019, 45(5): 101-108.

GAO Yuanyuan, HU Haimiao. Foggy image enhancement based on multi-block coordinated single-scale Retinex [J]. Journal of Beijing University of Aeronautics and Astronautics, 2019, 45(5): 101-108.

王萍, 张春, 罗颖昕. 一种雾天图像低对比度增强的快速算法 [J]. 计算机应用, 2006, 26(1): 152-153.

WANG Ping, ZHANG Chun, LUO Yingxin. Fast algorithm to enhance contrast of fog-degraded images [J]. Journal of Computer Applications, 2006, 26(1): 152-153.

祝培, 朱虹, 钱学明, 等. 一种有雾天气图像景物影像的清晰化方法 [J]. 中国图象图形学报, 2004, 9(1): 124-128.

ZHU Pei, ZHU Hong, QIAN Xueming, et al. An image clearness method for fog [J]. Journal of Image and Graphics, 2004, 9(1): 124-128.

詹翔, 周焰. 一种基于局部方差的雾天图像增强方法 [J]. 计算机应用, 2007, 27(2): 510-512.

ZHAN Xiang, ZHOU Yan. Algorithm based on local variance to enhance contrast of fog-degraded image [J]. Journal of Computer Applications, 2007, 27(2): 510-512.

TAN R T. Visibility in bad weather from a single image [C]∥26th IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2008: 4587643.

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

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

REN W, LIU S, ZHANG H, et al. Single image dehazing via multi-scale convolutional neural networks [C]∥14th European Conference on Computer Vision. Berlin, Germany: Springer-Verlag, 2016: 154-169.

CAI B, XU X. Dehaze net: an end-to-end system for single image haze removal [J]. IEEE Transactions on Image Processing, 2016, 25(11): 5187-5198.

张阿珍, 刘政林, 邹雪城, 等. 基于双3次插值算法的图像缩放引擎的设计 [J]. 微电子学与计算机, 2007, 24(1): 49-51.

ZHANG A’zhen, LIU Zhenglin, ZOU Xuecheng, et al. Design of image scaling engine based bicubic interpolation algorithm [J]. Microelectronics Computer, 2007, 24(1): 49-51.

MCCARTNEY E J. Optics of the atmosphere: scattering by molecules and particles [M]. New York, USA: John Wiley Sons Inc., 1976: 23-32.

NAYAR S K, NARASIMHAN S G. Vision in bad weather [C]∥Proceedings of the 1999 7th IEEE International Conference on Computer Vision. Piscataway, NJ, USA: IEEE, 1999: 820-827.

NARASIMHAN S G, NAYAR S K. Removing weather effects from monochrome images [C]∥Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2001: II186-II193.

PARTRIDGE M, JABRI M. Robust principal component analysis [C]∥Proceedings of the 10th IEEE Workshop on Neural Signal Processing. Piscataway, NJ, USA: IEEE, 2000: 289-298.

ZHUANG L, GAO H, LIN Z, et al. Non-negative low rank and sparse graph for semi-supervised learning [C]∥2012 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2012: 2328-2335.

ROCKAFELLAR R T. Augmented Lagrangians and applications of the proximal point algorithm in convex programming [J]. Mathematics of Operations Research, 1976, 1(2): 97-116.

BOYD S, PARIKH N, CHU E, et al. Distributed optimization and statistical learning via the alternating direction method of multipliers [J]. Foundations Trends in Machine Learning, 2011, 3(1): 1-122.

DAUBECHIES I, DEFRISE M, DE MOL C. An iterative thresholding algorithm for linear inverse problems with a sparsity constraint [J]. Communications on Pure and Applied Mathematics, 2004, 57(11): 1413-1457.

BERMAN D, TREIBITZ T, AVIDAN S. Non-local image dehazing [C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2016: 1674-1682.

HAUTIèRE N, TAREL J P, AUBERT D, et al. Blind contrast enhancement assessment by gradient ratioing at visible edges [J]. Image Analysis Stereology, 2008, 27(2): 87-95.

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

雾霾线求解透射率的二次优化方法

采用非相关字典学习的滚动轴承故障诊断方法

采用非线性块稀疏字典选择的视频总结

一种运用显著性检测的行为识别方法

采用试验设计方法的第三代CO2气体箔轴承箔片几何参数敏感性分析