基于光源区域自适应的夜间去雾方法

doi:10.11896/jsjkx.210300072

摘要/Abstract

摘要： 夜间有雾图像会导致图像质量下降,主要体现在夜间有雾图像光照不均、对比度较低且色偏严重,而人工光源的存在更是使得环境光呈现出不均匀性。现有的主流算法主要是针对白天图像进行处理,并不适用于夜间场景去雾处理,导致夜间去雾难度加大。针对上述问题,通过深入分析夜间有雾图像的成像特点,提出了一种新的夜间图像去雾算法。针对夜间有雾图像的色偏问题,提出了改进的暗通道先验算法(MRP)进行颜色校正,该方法单独操作每一个颜色通道进行颜色校正,从而可以减少由MRP引起的光源区域周围的光晕效应;针对夜间场景环境光不均匀性的特点,提出了基于有雾图像低频分量的最小-最大值滤波方法,以此来实现局部环境光的估计;针对最大反射率先验(DCP)估计透射率在光源处失效的问题,提出了一种基于光源区域自适应的透射率估计算法。实验结果表明,该算法在抑制光晕和光源区域发散的同时,能够较好地重现暗部细节,恢复图像具有较好的亮度和对比度,且色彩自然。相比暗通道先验,所提方法的峰值信噪比(PSNR)与结构相似性值(SSIM)平均提升了81.8%和26.5%。

关键词: 图像复原, 图像去雾, 夜间图像去雾

Abstract: Nighttime hazy image will cause image quality degradation,mainly reflected in the uneven illumination,low contrast and serious color deviation of nighttime hazy image,and artificial light source makes the ambient light nonuniformity.The existing mainstream algorithms are mainly for daytime image processing,but are not suitable for night scene dehazing processing.This makes night dehazing more difficult.In order to solve the above problems,this paper analyzes the imaging features of night image with fog and proposes a new night image dehazing algorithm.Aiming at the problem of color deviation of hazy images at night,this paper proposes an improved maximum reflectance prior algorithm (MRP) for color correction.This method operates each color channel separately for color correction,so as to reduce the halo effect around the light source area caused by MRP.As for the characteristics of nonuniformity of ambient light in night scene,a minimum reflectance prior algorithm based on low frequency component of hazy images is proposed.In order to solve the problem that the dark channel prior (DCP) estimation of transmittance fails at the light source,we propose a region adaptive algorithm of transmittance estimation based on the light source.The experimental results show that the proposed algorithm can suppress the halo and the divergence of the light source area.At the same time,it can better reproduce the dark details and restore the image with better brightness.

Key words: Image dehazing, Image restoration, Nighttime image dehazing

中图分类号:

TP391

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[J]. 计算机科学, 2021, 48(11A): 327-333. https://doi.org/10.11896/jsjkx.210300072

WANG Tong-sen, SHI Qin-zhong, WANG De-fa, DONG Shuo, YANG Guo-wei, YU Teng. Nighttime Image Dehazing Method Based on Adaptive Light Source Region[J]. Computer Science, 2021, 48(11A): 327-333. https://doi.org/10.11896/jsjkx.210300072

参考文献

[1]HE K M,SUN J,TANG X O.Single image haze removal using dark channel prior[C]//CVPR 2009:2009 IEEE Conference on Computer Vision and Pattern Recognition.Miami,FL,USA,2009:1956-1963.
[2]YANG A P,ZHAO M Q,WANG H X,et al.Nighttime Image Dehazing Based on Low-Pass Filtering and Joint Optimization of Multi-Feature[J].Acta Optica Sinica,2018,38(10):167-176.
[3]ZHANG J,CAO Y,FANG S,et al.Fast Haze Removal forNighttime Image Using Maximum Reflectance Prior[C]//CVPR 2017:2017 IEEE Conference on Computer Vision and Pattern Recognition.Honolulu,HI,2017:7016-7024.
[4]LI Y,TAN R T,BROWN M S.Nighttime Haze Removal with Glow and Multiple Light Colors[C]//2015 IEEE International Conference on Computer Vision(ICCV 2015).Santiago,2015:226-234.
[5]WANG J D,ZHANG W T,WANGZ R,et al.A fast aerizl image de-haze algorithm[J].Acta Aeronautica et Astronautica Sinica,2013,34(3):636-643.
[6]BERMAN D,TREITIBZ T,AVIDAN S.Non-local Image De-hazing[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR 2016).Las Vegas,NV,2016:1674-1682.
[7]QU Y,CHEN Y,HUANG J,et al.Enhanced Pix2pix Dehazing Network[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR 2019).Long Beach,CA,USA,2019:8152-8160.
[8]CHEN C,LI S,WANG Y,et al.Video saliency detection viaspatial-temporal fusion and low-rank coherency diffusion[J].IEEETransaction on Image Processing,2017,26(7):3156-3170.
[9]CHEN C,LI S,QIN H,et al.Bilevel feature learning for video saliency detection[J].IEEE Transaction on Multimedia,2018,20(20):3324-3336.
[10]CHENG C,WANG G,PENG C,et al.Improved robust video saliency detection based on long-term spatial-temporal information[J].IEEE Trans.Image Process,2020,29:1090-1100.
[11]CHEN C,WEI J,PENG C,et al.Improved saliency detection in RGB-D images using two-phase depth estimation and selective deep fusion[J].IEEE Trans.Image Process,2020,29:4296-4307.
[12]MA G,CHEN C,LI S,et al.Salient object detection via multiple instance joint re-learning[J].IEEE Trans.Multimedia,2020,22(2):324-336.
[13]XU X,YU T,XU X,et al.Variational total curvature model for multiplicative noise removal[J].IET Comput.Vis,2018,12(4):542-552.
[14]ISRAËL H,KASTEN F.Koschmieders theorie der horizontalen sichtweite[C]//Die Sichtweite Im Nebel Und Die Möglichkeiten Ihrer künstlichen Beeinflussung.Berlin,Germany:Springer,1959.
[15]ZHU Q,MAI J,SHAO L.A fast single image haze removal algorithm using color attenuation prior[J].IEEE Trans.Image Process,2015,24(11):3522-3533.
[16]PEI S C,LEE T Y.Nighttime haze removal using color transfer pre-processing and dark channel prior[C]//2012 19th IEEE International Conference on Image Processing(ICIP 2012).Orlando,FL,2012:957-960.
[17]LI Y,TAN R T,BROWN M S.Nighttime haze removal with glow and multiple light colors[C]//2015 IEEE International Conference on Computer Vision(ICCV 2015).Santiago,2015:226-234.
[18]ANCUTI C,ANCUTI C O,DE VLEESCHOUWER C,et al.Night-time dehazing by fusion[C]//2016 IEEE International Conference on Image Processing(ICIP 2016).Phoenix,AZ,2016:2256-2260.
[19]YU T,SONG K,MIAO P,et al.Nighttime single image dehaz-ing via pixel-wise alpha blending[J].IEEE Access,2019,7:114619-114630.
[20]ZHANG J,CAO Y,WANG Z.Nighttime haze removal based on a new imaging model[C]//2014 IEEE International Conference on Image Processing(ICIP 2014).Paris,2014:4557-4561.
[21]GUO X,LI Y,LING H.LIME:Low-light image enhancement via illumination map estimation[J].IEEE Trans.Image Process.,2017,26(2):982-993.
[22]KUANAR S,RAO K R,MAHAPATRA D,et al.Night timehaze and glow removal using deep dilated convolutional network[EB/OL].[2021-02-10].https://arxiv.org/abs/1902.008-55v1.
[23]SHI Z,FENG Y,ZHAO M,et al.A joint deep neural networks-based method for single nighttime rainy image enhancement[J].Neural Comput.Appl.,2020,32(7):1913-1926.
[24]WEI C,WANG W,YANG W,et al.Deep retinex decomposition for low-light enhancement[EB/OL].[2021-02-10].https://arxiv.org/abs/1808.04560.
[25]LOU W,LI Y,YANG G,et al.Integrating Haze Density Features for Fast Nighttime Image Dehazing[J].IEEE Access,2020,8:113318-113330.
[26]HUANG W J,LI J,QI C.A Defogging Algorithm for Dense Fog Images via Low-Rank and Dictionary Expression Decomposition[J].Journal of Xi'an Jiaotong University,2020,54(4):118-125.
[27]TANG X Q,FAN C N,LIU X.A Fast Removing Algorithm of Single Image Using Edge Preserving Filtering[J].Journal of Xi'an Jiaotong University,2015,49(3):143-150.
[28]XIAO J S,SHEN M Y,LEI J F,et al.Image Conversion Algorithm for Haze Scene Based on Generative Adversarial Networks[J].Chinese Journal of Computers,2020,43(1):165-176.
[29]WANG Y F,WANG Y Y.MP-CGAN:night single image dehazing algorithm based on Msmall-Patch training[J].Journal of Computer Applications,2020,40(3):865-871.
[30]DUAN L.Nighttime Image Dehazing Based on Illumination Estimation and Fast Guided Filter[J].Modern Computer,2019(36):76-81.
[31]QIU D F,HUANG G H,LIU X,et al.Dark channel haze removal based on adaptive transmission and airlight estimation[J].Journal of Computer Applications,2017,37(S1):176-179,186.
[32]YU S Y,ZHU H.Lighting model construction and haze removal for nighttime image[J].Optics and Precision Engineering,2017,25(3):729-734.
[33]NARASIMHAN S G,NAYAR S K.Vision and the Atmosphere[J].International Journal of Computer Vision,2002,48(3):233-254.

相关文章 15

[1]	何涛, 赵停, 徐鹤. 基于暗通道先验的单幅图像去雾新算法 Novel Algorithm of Single Image Dehazing Based on Dark Channel Prior 计算机科学, 2021, 48(7): 219-224. https://doi.org/10.11896/jsjkx.200700160
[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]	李泽文, 李子铭, 费天禄, 王瑞琳, 谢在鹏. 基于残差生成对抗网络的人脸图像复原 Face Image Restoration Based on Residual Generative Adversarial Network 计算机科学, 2020, 47(6A): 230-236. https://doi.org/10.11896/JsJkx.190400118
[5]	张墨华, 彭建华. 基于狄利克雷过程混合模型的内外先验融合 Integration of Internal and External Priors Based on Dirichlet Process Mixture Model 计算机科学, 2020, 47(5): 172-180. https://doi.org/10.11896/jsjkx.190400060
[6]	邹鹏, 谌雨章, 陈龙彪, 曾张帆. 基于神经网络的光照分布预测夜视复原算法 Night Vision Restoration Algorithm Based on Neural Network for Illumination Distribution Prediction 计算机科学, 2019, 46(11A): 329-333.
[7]	张茗琪, 曹国, 陈强, 孙权森. 基于改进逆滤波的衍射成像光谱仪图像复原方法 Image Restoration Method Based on Improved Inverse Filtering for Diffractive Optic Imaging Spectrometer 计算机科学, 2019, 46(1): 86-93. https://doi.org/10.11896／j.issn.1002-137X.2019.01.013
[8]	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.
[9]	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
[10]	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
[11]	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
[12]	许影,李强懿. 基于稀疏特性的盲二值图像去模糊 Blind Binary Image Deconvolution Based on Sparse Property 计算机科学, 2018, 45(3): 253-257. https://doi.org/10.11896/j.issn.1002-137X.2018.03.040
[13]	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
[14]	马洪华,黄永林,丁岩岩. 用于彩色图像复原的带有高阶耦合项的TV模型 Total Variance with High-order Coupling Term for Color Image Restoration 计算机科学, 2016, 43(Z6): 214-216. https://doi.org/10.11896/j.issn.1002-137X.2016.6A.051
[15]	赵志刚,陈莹莹,赵毅,张维忠,吕慧显,潘振宽. 基于边缘先验模型的运动去模糊 Motion Deblurring Based on Edge Prior Model 计算机科学, 2015, 42(5): 305-308. https://doi.org/10.11896/j.issn.1002-137X.2015.05.062

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed