计算机科学 ›› 2021, Vol. 48 ›› Issue (7): 219-224.doi: 10.11896/jsjkx.200700160

• 计算机图形学&多媒体 • 上一篇    下一篇

基于暗通道先验的单幅图像去雾新算法

何涛1, 赵停1, 徐鹤2,3   

  1. 1 南京邮电大学电子与光学工程学院 南京210023
    2 南京邮电大学计算机学院、软件学院、网络空间安全学院 南京 210023
    3 江苏省无线传感网高技术研究重点实验室 南京210003
  • 收稿日期:2020-07-26 修回日期:2020-10-06 出版日期:2021-07-15 发布日期:2021-07-02
  • 通讯作者: 徐鹤(xuhe@njupt.edu.cn)
  • 基金资助:
    国家重点研发计划项目(2019YFB2103003);国家自然科学基金(61672296,61872196,61872194,61902196);江苏省科技支撑计划项目(BE2019740);江苏省高等学校自然科学研究重大项目(18KJA520008);江苏省六大人才高峰高层次人才项目(RJFW-111).

Novel Algorithm of Single Image Dehazing Based on Dark Channel Prior

HE Tao1, ZHAO Ting1, XU He2,3   

  1. 1 College of Electronic and Optical Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210023,China
    2 School of Computer Science,Nanjing University of Posts and Telecommunications,Nanjing 210023,China
    3 Jiangsu Key Laboratory of Wireless Sensor Network High Technology Research,Nanjing 210003,China
  • Received:2020-07-26 Revised:2020-10-06 Online:2021-07-15 Published:2021-07-02
  • About author:HE Tao,born in 1972,Ph.D,lecturer.His main research interests include the survivability of wireless sensor networks,the spectrum allocation of mobile cognitive radio networks,and the QoS routing of computer networks.(het@njupt.edu.cn)
    XU He,born in 1985,Ph.D,associate professor,is a member of China Computer Federation.His main research interests include Internet of Things technology application and information security.
  • Supported by:
    National Key R&D Program of China(2019YFB2103003),National Natural Science Foundation of China(61672296,61872196,61872194,61902196),Scientific and Technological Support Project of Jiangsu Province(BE2019740),Major Natural Science Research Projects in Colleges and Universities of Jiangsu Province(18KJA520008) and Six Talent Peaks Project of Jiangsu Province(RJFW-111).

摘要: 由于暗通道先验去雾算法会使天空等明亮区域产生颜色失真、偏移等问题,对此文中提出基于暗通道先验的单幅图像去雾新算法,提高了图像去雾效果。首先,根据图像的大小设计了一种自适应滤波窗口;其次,为了防止图像中的高亮像素对大气光值估计的影响,利用变差函数去除这些高亮像素,并结合去除高亮像素后图像的暗通道图,估计大气光值;然后,提出了一种结合结构相似性的暗通道先验去雾改进算法,并对透射率进行优化、修正;接着,利用大气散射模型恢复出无雾图像;最后,利用RGB模型和HIS模型的相互转化,增强恢复图像的亮度。实验结果表明,该算法不仅能对图中景物进行较好的去雾,还能较好地处理天空等明亮区域,使处理后的图像有很好的视觉效果。

关键词: 暗通道先验, 导向滤波, 结构相似性, 明亮区域, 图像去雾

Abstract: Because the dark channel prior defogging algorithm will cause color distortion and offset in bright areas such as the sky,a novel algorithm of single image dehazing based on dark channel prior is proposed to improve the image defogging effect.Firstly,according to the size of the image,an adaptive filtering window is designed.Next,in order to prevent the influence of the highlight pixels in the image on the estimation of the atmospheric light value,the variogram is used to remove the highlight pi-xels,and the atmospheric light value is estimated by combining the dark channel map of the image after removing the highlight pi-xel.Then,an improved dark channel prior defogging algorithm combined with structural similarity is proposed,and the transmittance is optimized and corrected.And then,the atmospheric scattering model is used to recover the fog-free image.Finally,the mutual conversion of the RGB model and the HIS model are used to enhance the brightness of the restored image.The experimental results show that the proposed algorithm can not only better dehaze the scene in the picture,but also better deal with bright areas such as the sky,so that the processed image has a good visual effect.

Key words: Bright area, Dark channel prior, Guided filter, Image dehazing, Structural similarity

中图分类号: 

  • TP391
[1]HE K M,SUN J,TANG X O.Single image haze removal using dark channel prior[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(12):2341-2353.
[2]CHEN Y,ZHU M.Multi-sub-histogram equalization low-lightimage enhancement and FPGA implementation [J].China Optics,2014,7(2):225-233.
[3]XIAO Y F.Research on image Enhancement recovery algorithm based on retinex theory [D].Shanghai:Shanghai Jiaotong University,2007.
[4]SUN Y B,XIAO L,WEI Z H,et al.Outdoor image dehazing method based on partial differential equations [J].Journal of System Simulation,2007(16):3739-3744,3769.
[5]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.
[6]TAN R T.Visibility in bad weather from a single image [EB/OL].[2010-02-25].http://people.cs.uu.nl/robby/fog/index.html.
[7]FATTAL R.Single image dehazing [EB/OL].[2010-02-25].http://www.cs.huji.ac.il/~raananf/projects/defog/index.html.
[8]HE K M,SUN J,TANG X O.Guided image Filtering[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2013,35(6):1397-1409.
[9]JIANG J G,HOU T F,QI M B.Image dehazing algorithm based on dark primary color prior[J].Journal of Circuits and Systems,2011,16(2):7-12.
[10]NARASIMHAN S G,NAYAR S K.Vision and the atmosphere [J].International Journal of Computer Vision,2002,48(3):233-254.
[11]TAN L J.Research on improved dark channel prior single image dehazing algorithm for sky recognition[J].Mini-micro systems,2019,40(1):210-214.
[12]BAO B,LI Y G.An improved image defogging algorithm based on dark channel prior [J].Computer and Modernization,2019(2):27-30,36.
[13]ZHU W W ,YANG L,ZANG X X .Application of Dark Channel Prior Principle to Licensed Plate Detection in Foggy Weather [C]//2018 IEEE 3rd Advanced Information Technology,Electronic and Automation Control Conference.2018:2591-2595.
[14]XIE L,XIONG G,YU B,et al.A new method for dehazing atmospheric degradation images based on the dark channel prior [J].Control Engineering,2020,27(2):207-211.
[15]LIU Q.A Light intensity reverse algorithm for improving dark channel prior dehazing[C]//2018 11th International Congress on Image and Signal Processing,BioMedical Engineering and Informatics(CISP-BMEI).Beijing,China,2018:1-9.
[16]QIU D F,HUANG G H,LIU X,et al.Dark channel dehazing with adaptive estimation of tranmittance and atmospheric light [J].Journal of Computer Applications,2017,37(S1):176-179,186.
[17]LI K,LAN S Y,ZHANG J W,et al.Improved image dehazing algorithm based on dark primary color prior [J].Computer Technology and Development,2015,25(2):6-11.
[18]SHAO M S.Research on Image Dehazing Based on Hybrid Dark Channel Algorithm[J].Acta Metrology,2020,41(7):796-800.
[19]LI Z X,GUO Y,JI J.Design and implementation of an image defogging platform based on histogram [J].Computer Knowledge and Technology,2020,16(6):180-182.
[20]ZHANG J W,WANG X Y,YANG C H,et al.Image dehazing based on dark channel prior and brightness enhancement for agricultural remote sensing images from consumer-grade cameras[J].Computers and Electronics in Agriculture,2018,151:196-206.
[21]WANG Z,HOU G J,PAN Z K,et al.Single image dehazing and denoising combining dark channel prior and variational models[J].IET Computer Vision,2018,12(4):393-402.
[22]ZHANG X C,SUN L J.Image defogging algorithm based onguided filtering and variation function [J].Computer Technology and Development,2019,29(6):23-26.
[1] 王同森, 史勤忠, 王得法, 董硕, 杨国为, 于腾.
基于光源区域自适应的夜间去雾方法
Nighttime Image Dehazing Method Based on Adaptive Light Source Region
计算机科学, 2021, 48(11A): 327-333. https://doi.org/10.11896/jsjkx.210300072
[2] 杨坤, 张娟, 方志军.
基于多补丁和多尺度层级聚合网络的快速非均匀图像去雾
Multi-patch and Multi-scale Hierarchical Aggregation Network for Fast Nonhomogeneous ImageDehazing
计算机科学, 2021, 48(11): 250-257. https://doi.org/10.11896/jsjkx.200900058
[3] 朱珍, 黄锐, 臧铁钢, 卢世军.
基于加权近红外图像融合的单幅图像除雾方法
Single Image Defogging Method Based on Weighted Near-InFrared Image Fusion
计算机科学, 2020, 47(8): 241-244. https://doi.org/10.11896/jsjkx.200300068
[4] 刘洋, 张杰, 张慧.
一种改进的Retinex算法在图像去雾中的研究与应用
Study and Application of Improved Retinex Algorithm in Image Defogging
计算机科学, 2018, 45(6A): 242-243.
[5] 崔倩男,田小平,吴成茂.
基于引导滤波改进的暗原色去雾算法
Improved Algorithm of Haze Removal Based on Guided Filtering and Dark Channel Prior
计算机科学, 2018, 45(5): 285-290. https://doi.org/10.11896/j.issn.1002-137X.2018.05.049
[6] 张文博,侯晓荣.
基于高斯分布的大气光估计算法
Estimation Algorithm of Atmospheric Light Based on Gaussian Distribution
计算机科学, 2018, 45(4): 301-305. https://doi.org/10.11896/j.issn.1002-137X.2018.04.051
[7] 赵胜楠,魏伟波,潘振宽,李帅.
基于暗原色先验与MTV模型的单幅彩色图像去雾
Single Color Image Dehazing Based on Dark Channel Prior and MTV Model
计算机科学, 2018, 45(3): 274-276. https://doi.org/10.11896/j.issn.1002-137X.2018.03.044
[8] 苗启广,李宇楠.
图像去雾霾算法的研究现状与展望
Research Status and Prospect of Image Dehazing
计算机科学, 2017, 44(11): 1-8. https://doi.org/10.11896/j.issn.1002-137X.2017.11.001
[9] 黄涛,黄仁,张坤.
一种改进的协同过滤推荐算法
Improved Collaborative Filtering Recommendation Algorithm
计算机科学, 2016, 43(Z6): 400-403. https://doi.org/10.11896/j.issn.1002-137X.2016.6A.095
[10] 陈丽,郭玉坤,李金屏.
一种基于Sigmoid函数的抑制Halo效应的有效算法
Effective Algorithm to Inhibit Halo Effect Based on Sigmoid Function
计算机科学, 2015, 42(11): 112-117. https://doi.org/10.11896/j.issn.1002-137X.2015.11.024
[11] 田洪金,战荫伟.
基于自适应分块和SSIM的运动目标检测
Moving Object Detection Based on Adaptive Image Blocking and SSIM
计算机科学, 2014, 41(2): 119-122.
[12] 张瑞雪,宋明秋,公衍磊.
逆序解析DOM树及网页正文信息提取
Parsing DOM Tree Reversely and Extracting Web Main Page Information
计算机科学, 2011, 38(4): 213-215.
[13] 吉国力,倪晓明.
基于Haar小波变换高频特征的图像质量评价算法
Image Quality Assessment Algorithm Based on High Frequency Band of Haar Wavelet Transform
计算机科学, 2009, 36(10): 262-264.
[14] 郑浩森 汤胤 彭宏 郑启伦.
范例推理结构相似性研究

计算机科学, 2004, 31(6): 153-155.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!