计算机科学 ›› 2021, Vol. 48 ›› Issue (11A): 327-333.doi: 10.11896/jsjkx.210300072
王同森1, 史勤忠1, 王得法1, 董硕2, 杨国为1, 于腾1
WANG Tong-sen1, SHI Qin-zhong1, WANG De-fa1, DONG Shuo2, YANG Guo-wei1, YU Teng1
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%。
中图分类号:
[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. |
[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 |
|