首页 > 论文 > 光学学报 > 38卷 > 4期(pp:0410002--1)

基于暗原色先验的图像去雾方法研究

Study On Image Dehazing Methods Based On Dark Channel Prior

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

摘要

基于暗原色先验理论,提出一种单幅图像去雾算法,并对其中的可调参数进行讨论,分析参数变化对去雾效果的影响。针对原算法中提到不用特殊处理的天空区域进行验证,发现此区域需要进行单独处理,通过设置阈值将天空区域隔离出来进行处理,并取得了较好的效果。对引入的导向滤波算法进行研究,分析算法中各项参数对算法实时性的影响。为了进一步提高算法实时性,对图像进行缩小处理,以减少求取透射率所需的时间,再利用插值法将透射率图还原至原图尺寸,从而得到无雾图像。实验证明,此方法在保证去雾效果的前提下,可将算法整体运算时间降低85.7%。

Abstract

Based on the dark channel prior, we propose a dehazing algorithm for single image, discuss the adjustable parameters of the algorithm, and analyze the impact of parameter variation on the final dehazing results. In the primal algorithm, the sky area is mentioned as no need of special handling. However, we find that this area needs to be treated separately. We set threshold to isolate the sky area separately and receive better effect. Meanwhile, we study on the introduced guided-filter, and analyze the impact of parameters on the real-time performance of the algorithm. In order to improve the real-time performance of the algorithm, we reduce the picture firstly in order to shorten the calculation time, and then enlarge the image by image interpolation method to get haze-free image. The experimental results show that the operation time of the algorithm can be reduced by 85.7% with the premise of image haze removal.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TP751

DOI:10.3788/AOS201838.0410002

所属栏目:图像处理

基金项目:浙江省自然科学基金(LY14F040003)

收稿日期:2017-09-26

修改稿日期:2017-10-31

网络出版日期:--

作者单位    点击查看

郭翰:浙江工业大学理学院应用物理系, 浙江 杭州 310023
徐晓婷:浙江工业大学理学院应用物理系, 浙江 杭州 310023
李博:浙江工业大学理学院应用物理系, 浙江 杭州 310023

联系人作者:李博(libo@zjut.edu.cn)

备注:郭翰(1993-),男,硕士研究生,主要从事图像处理方面的研究。E-mail: 1033538753@qq.com

【1】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.

【2】Liu H B, Yang J, Wu Z P, et al. A fast single image dehazing method based on dark channel prior and Retinex theory[J]. Acta Automatica Sinica, 2015, 41(7): 1264-1273.
刘海波, 杨杰, 吴正平, 等. 基于暗原色先验和Retinex理论的快速单幅图像去雾方法[J]. 自动化学报, 2015, 41(7): 1264-1273.

【3】Chu J, Wang H B, Tao L, et al. Novel algorithm for single haze image restration based on guided image filtering[J]. Computer Engineering and Applications, 2015, 51(21): 155-160.
楚君, 王华彬, 陶亮, 等. 基于引导滤波器的单幅雾天图像复原算法[J]. 计算机工程与应用, 2015, 51(21): 155-160.

【4】He K M, Sun J, Tang X O. Single image haze removal using dark channel prior[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2009: 1956-1963.

【5】Huang L H. A new single image dehazing algorithm[J]. Acta Photonica Sinica, 2011, 40(9): 1519-1422.
黄黎红. 单幅图像的去雾新算法[J]. 光子学报, 2011, 40(9): 1519-1422.

【6】Yang H, Wang J. Color image contrast enhancement by co-occurrence histogram equalization and dark channel prior[C]. 2010 3rd International Congress on Image and Signal Processing (CISP), IEEE, 2010, 2: 659-663.

【7】Jiang J G, Hou T F, Qi M B. A improved image dehazing algorithm based on dark channel prior[J]. Journal of Circuits and Systems, 2011, 16(2): 7-12.
蒋建国, 侯天峰, 齐美彬. 改进的基于暗原色先验的图像去雾算法[J]. 电路与系统学报, 2011, 16(2): 7-12.

【8】Chu H L, Li Y X, Zhou Z M, et al. Optimized fast dehazing method based on dark channel prior[J]. Acta Electronica Sinica, 2013, 41(4): 791-797.
褚宏莉, 李元祥, 周则明, 等. 基于黑色通道的图像快速去雾优化算法[J]. 电子学报, 2013, 41(4): 791-797.

【9】Tarel J P, Hautiere N. Fast visibility restoration from a single color or gray level image[C]. IEEE 12th International Conference on Computer Vision, 2009: 2201-2208.

【10】Wang J D, Zhang W Y, Wang Z R, et al. A fast aerial image dehazing algorithm[J]. Acta Aeronautica et Astronautica Sinica, 2013, 34(3): 636-643.
王敬东, 张文涛, 王子瑞, 等. 一种快速航空图像去雾算法[J]. 航空学报, 2013, 34(3): 636-643.

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

【12】van Herk M. A fast algorithm for local minimum and maximum filters on rectangular and octagonal kernels[J]. Pattern Recognition Letters, 1992,13: 517-521.

【13】Ji X Q, Dai M, Sun L N, et al. Research on the image haze removal algorithm based on the prior dark-channel[J]. Journal of Optoelectronics·Laser, 2011, 22(6): 926-930.
嵇晓强. 戴明, 孙丽娜, 等. 暗原色先验图像去雾算法研究[J]. 光电子·激光, 2011,22(6): 926-930.

【14】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.

【15】Ma Z L, Wen J, Hao L L. Video image dehazing algorithm for surface ship scenes[J]. Systems Engineering and Electronics, 2014, 36(9): 1860-1867.
马忠丽, 文杰, 郝亮亮. 海面舰船场景的视频图像海雾去除算法[J]. 系统工程与电子技术, 2014, 36(9): 1860-1867.

【16】Bissonnette L. Imaging through fog and rain[J]. Optical Engineering, 1992, 31(5): 1045-1052.

【17】Dai S B, Xu W, Pu Y J, et al. Remote sensing image dehazing 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.

【18】Li K, Liu H, Wang D, et al. A halo-free algorithm for image dehazing[J]. Computer and Information Technology, 2016, 24(6): 7-11.
李可, 刘辉, 汪丹, 等. 一种消除halo效应的去雾算法[J]. 电脑与信息技术, 2016, 24(6): 7-11.

【19】Huang X J, Lai Y D, Chen F. Fast single image haze removal algorithm[J]. Computer Application, 2010, 30(11): 3029-3031.
黄晓军, 来彦栋, 陈奋. 快速去除单幅图像雾霾的算法[J]. 计算机应用, 2010, 30(11): 3029-3031.

【20】Wang Y T, Feng Z L. Single image fast dehazing method based on dark channel prior[J]. Journal of Computer Applications, 2016, 36(12): 3406-3410.
王雅婷, 冯子亮. 基于暗原色先验的单幅图像快速去雾算法[J]. 计算机应用, 2016, 36(12): 3406-3410.

【21】Wang P, Zhang C, Luo Y X. Fast algorithm to enhance contrast of fog degraded in ages[J]. Computer Applications, 2006, 26(1): 152-154.
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): 152-154.

【22】Oakley J P, Satherley B L. Improving image quality in poor visibility conditions using a physical model for contrast degradation[J]. IEEE Transactions on Image Processing, 1998, 7(2): 167-179.

【23】Tan R T. Visibility in bad weather from a single image[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2008: 1-8.

【24】Fattal R. Single image dehazing[J]. ACM Transactions on Graphics (TOG), 2008, 27(3): 1-9.

【25】Narasimhan S G, Nayar S K. Interactive (de) weathering of an image using physical models[C]. IEEE Workshop on Color and Photometric Methods in Computer Vision, 2003: 1-8.

【26】Zhu Y H, Fang B, Zhang H Q. Image of road de-weathering based on physical model[J]. Journal of Computer Applications, 2010, 30(1): 156-158.
朱瑜辉, 方滨, 张会清. 基于物理模型的雾霾天道路图像清晰化[J]. 计算机应用, 2010, 30(1): 156-158.

【27】Song Y C, Luo H B, Hui B, et al. Haze removal using scale adaptive dark channel prior[J]. Infrared and Laser Engineering, 2016, 45(9): 0928002.
宋颖超, 罗海波, 惠斌, 等. 尺度自适应暗原色先验去雾方法[J]. 红外与激光工程, 2016, 45(9): 0928002.

引用该论文

Guo Han,Xu Xiaoting,Li Bo. 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

被引情况

【1】曾致远,周亚同,池越,史芳宁. 天空优化的数字图像暗通道先验去雾算法. 激光与光电子学进展, 2018, 55(8): 81010--1

【2】杨爱萍,赵美琪,王海新,鲁立宇. 基于低通滤波和多特征联合优化的夜间图像去雾. 光学学报, 2018, 38(10): 1010006--1

【3】祝振敏,裴爽,陈世明,张福民. 基于偏振信息的强反射工件高光去除及视觉测量方法. 光学学报, 2018, 38(11): 1112005--1

【4】田青,袁曈阳,杨丹,魏运. 基于暗通道去雾和深度学习的行人检测方法. 激光与光电子学进展, 2018, 55(11): 111007--1

【5】杨爱萍,王海新,王金斌,赵美琪,鲁立宇. 基于透射率融合与多重导向滤波的单幅图像去雾. 光学学报, 2018, 38(12): 1210001--1

【6】姜沛沛,杨燕. 基于高斯衰减的自适应线性变换去雾算法. 激光与光电子学进展, 2019, 56(10): 101002--1

【7】苏畅,毕国玲,金龙旭,聂婷,梁怀丹. 基于暗通道图像质心偏移量的去雾算法. 光学学报, 2019, 39(5): 533001--1

【8】张文飞,满忠胜,葛筱璐,邢飞,付圣贵. 一种快速实现的偏振光学去雾方法. 激光与光电子学进展, 2019, 56(14): 141103--1

【9】曲晨,毕笃彦. 基于多先验约束的雾霾图像复原. 激光与光电子学进展, 2020, 57(18): 181014--1

【10】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. 光学学报, 2020, 40(2): 210003--1

【11】张文飞,任立勇,邢飞,张芳,葛筱璐,王国梅,付圣贵. 基于离散余弦变换金字塔分解的新型偏振光学去雾技术. 激光与光电子学进展, 2020, 57(6): 61102--1

【12】刘增力,付钰. 基于透射率自适应约束修正的图像去雾算法. 激光与光电子学进展, 2020, 57(16): 161003--1

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