融合变分偏微分方程的单幅彩色图像去雾

周理; 毕笃彦; 何林远

doi:10.3788/OPE.20152305.1466

您当前的位置：

首页 >

文章列表页 >

融合变分偏微分方程的单幅彩色图像去雾

信息科学 | 更新时间：2020-08-13

- 融合变分偏微分方程的单幅彩色图像去雾
- Single color image dehazing using variational partial differential equation
- 光学精密工程 2015年23卷第5期页码：1466-1473
- 作者机构：
  
  空军工程大学航空航天工程学院通信导航教研室,陕西西安,710038
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目(No.61372167)()
- DOI：10.3788/OPE.20152305.1466
  中图分类号： TP391.41
- 收稿日期：2014-11-25，
  
  修回日期：2014-12-09，
  
  纸质出版日期：2015-05-25
- 稿件说明：
移动端阅览
周理, 毕笃彦, 何林远. 融合变分偏微分方程的单幅彩色图像去雾[J]. 光学精密工程, 2015,23(5): 1466-1473

ZHOU Li, BI Du-yan, HE Lin-yuan. Single color image dehazing using variational partial differential equation[J]. Editorial Office of Optics and Precision Engineering, 2015,23(5): 1466-1473
周理, 毕笃彦, 何林远. 融合变分偏微分方程的单幅彩色图像去雾[J]. 光学精密工程, 2015,23(5): 1466-1473 DOI： 10.3788/OPE.20152305.1466.

ZHOU Li, BI Du-yan, HE Lin-yuan. Single color image dehazing using variational partial differential equation[J]. Editorial Office of Optics and Precision Engineering, 2015,23(5): 1466-1473 DOI： 10.3788/OPE.20152305.1466.

摘要

对单幅雾霾图像的图像处理问题进行了分析。鉴于现有方法不能很好恢复场景深度变化较大的图像

本文融合大气衰减模型与变分偏微分方程

提出了一种单幅彩色图像去雾算法。该算法利用数学形态学中的中值集算子构造局部白平衡处理

精确估计大气光参数。设计了一种全新的平滑性度量范数

尝试从全变分的角度建立目标图像的变分能量模型

继而通过偏微分方程将其转化为欧拉-拉格朗日方程。最后

利用交替半二次型算法求解欧拉-拉格朗日方程

以提升算法流程的整体运行速度

使其可维持在105 ms左右。以图像熵和平均梯度为图像质量评价指标进行了仿真实验

结果表明

本文算法使评价指标提升达60%

而对照组则均保持在15%至30%左右。该算法对于场景深度变化较大的图像的局部区域恢复效果明显

可以满足应用要求。

Abstract

Imaging processing for single color hazing images was researched. Since the current methods could not recover the kind of images with the scene depth changing fiercely

a single color image dehazing algorithm was introduced on the basis of the atmosphere attenuate model and the variational partial differential equation. In this method

the median set operator in morphology was used to construct local white balance operator and to estimate the atmospherical optical parameters precisely. Then

a novel smoothness measure norm was designed to build up a variational energy model of the target image based on the total variation theory. In addition

the model was converted from partial differential equation into the Euler-Lagrange equation. Finally

the alternate semi-quadratic algorithm was used to solve the Euler-Lagrange equation

by which the operation speed of the algorithm was improved to be at 105 ms. The means of image entropy and average gradient were taken as the evaluation indexes

and simulation results show that proposed method triggers an increase by 60% in operation performance while other control groups keep the improvement in 15% to 30%. This method improves the local region obviously and reaches the application requirement.

关键词

Keywords

references

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. (in Chinese)

薛模根, 周浦城, 张洪坤. 利用方向延伸专家场的单幅雾天图像复原[J]. 计算机辅助设计与图形学学报, 2014, 26(5):782-787. XUE M G, ZHOU P CH, ZHANG H K. Single foggy image restoration using orientation extended fields of experts [J]. Journal of Computer-Aided Design & Computer Graphics, 2014, 26(5):782-787. (in Chinese)

陈洪财. 适于LCM应用的彩色图像全局不失真增强算法[J]. 液晶与显示, 2013, 28(3): 446-449. CHEN H CH. Color image globally without distortion enhancement algorithms suitable for LCM applications [J]. Chinese Journal of Liquid Crystals and Displays, 2013, 28(3): 446-449.(in Chinese)

赵凡, 张葆. 基于FPGA的航拍图像实时增强[J]. 液晶与显示, 2014, 29(5): 793-799. ZHAO F, ZHANG B. Aerial image enhancement processing based on FPGA [J]. Chinese Journal of Liquid Crystals and Displays, 2014, 29(5): 793-799. (in Chinese)

周妍, 李庆武, 霍冠英. 基于非下采样Contourlet变换系数直方图匹配的自适应图像增强[J]. 光学精密工程, 2014, 22(8): 2214-2222. ZHOU Y, LI Q W, HUO G Y. Adaptive image enhancement based on NSCT coefficient histogram matching [J]. Opt. Precision Eng., 2014, 22(8): 2214-2222. (in Chinese)

赵宏宇, 肖创柏, 禹晶. 马尔科夫随机场模型下的Retinex夜间彩色图像增强[J]. 光学精密工程, 2014, 22(4): 1048-1055. ZHAO H Y, XIAO C B, YU J. A Retinex algorithm for night color image enhancement by MRF [J]. Opt. Precision Eng., 2014, 22(4): 1048-1055. (in Chinese)

FATTAL R. Single image dehazing[J].Proceedings of SIGGRAPH, 2008, 27(3):1-9.

HE K, SUN J, TANG X. Single image haze removal using dark channel prior [C]. Proc. of 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2009: 1956-1963.

HAUTIÉRE N, TAREL J P, HALMAOUI H. Enhanced fog detection and free-space segmentation for car navigation [J]. Machine Vision and Applications, 2014, 25: 667-679.

GUO F, TANG J, CAI Z X. Image dehazing based on haziness analysis [J]. International Journal of Automation and Computing, 2014, 11(1): 78-86.

NARASIMHAN S G, NAYAR S K. Contrast restoration of weather degraded images[J]. PAMI, 2003, 25(6): 713-724.

WANG J W, WU H N, LI H X. Distributed proportional-spatial derivative control of nonlinear parabolic systems via fuzzy PDE modeling approach [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 2012, 42(3):927-938.

BENK J, PFLUGER D. Hybrid parallel solutions of the Black-Scholes PDE with the truncated combination technique[C]. International Conference on High Performance Computing and Simulation (HPCS), 2012: 678-683.

高山, 王星, 程嗣怡. 交叉视觉皮质模型中向心自动波的实现[J]. 西安电子科技大学学报:自然科学版, 2013, 40(1):170-176. GAO SH, WANG X, CHENG S Y. Implementation of the centripetal auto-wave in an intersecting cortical model [J]. Journal of xi dian University:Natural Science, 2013, 40(1):170-176.

RUDINL, OSHER S, FATIME E. Nonlinear total variation bases noise removal algorithm [J]. Physisca D, 1992, 60(1):259-268.

AUBERT G, VESE A. A variational method in image recovery [J]. SIAM Journal of Numerical Analysis, 1997, 35(5):1948-1978.

浏览量

795

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

频域特征蒸馏的双尺度融合图像去雾网络

全局和局部特征融合的图像去雾

基于偏振度优化与大气光校正的图像去雾

使用改进型大气散射模型的双阶段图像修复

适应性双通道先验的图像去雾方法