高级搜索

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于均值不等关系优化的自适应图像去雾算法

杨燕 王志伟

杨燕, 王志伟. 基于均值不等关系优化的自适应图像去雾算法[J]. 电子与信息学报, 2020, 42(3): 755-763. doi: 10.11999/JEIT190368
引用本文: 杨燕, 王志伟. 基于均值不等关系优化的自适应图像去雾算法[J]. 电子与信息学报, 2020, 42(3): 755-763. doi: 10.11999/JEIT190368
Yan YANG, Zhiwei WANG. Adaptive Image Dehazing Algorithm Based on Mean Unequal Relation Optimization[J]. Journal of Electronics & Information Technology, 2020, 42(3): 755-763. doi: 10.11999/JEIT190368
Citation: Yan YANG, Zhiwei WANG. Adaptive Image Dehazing Algorithm Based on Mean Unequal Relation Optimization[J]. Journal of Electronics & Information Technology, 2020, 42(3): 755-763. doi: 10.11999/JEIT190368

基于均值不等关系优化的自适应图像去雾算法

doi: 10.11999/JEIT190368
基金项目: 国家自然科学基金(61561030),甘肃省财政厅基本科研业务费基金(214138),兰州交通大学教改基金(160012)
详细信息
    作者简介:

    杨燕:女,1972年生,博士,教授、硕士生导师,主要研究方向为数字图像处理、智能信息处理、语音信号处理

    王志伟:男,1996年生,硕士生,主要研究方向为数字图像处理、计算机视觉

    通讯作者:

    杨燕 yangyantd@mail.lzjtu.cn

  • 中图分类号: TN911.73; TP391.41

Adaptive Image Dehazing Algorithm Based on Mean Unequal Relation Optimization

Funds: The National Natural Science Foundation of China (61561030), The Fundamental Research Funds for the Gansu Provincial Finance Department (214138), The Research Fund of Teaching Reform Project of Lanzhou Jiao Tong University (160012)
  • 摘要:

    针对暗通道先验去雾算法的不足,如天空区域透射率估计过小和在景深突变处易发生光晕效应,该文提出一种新颖且高效的去雾算法。首先通过几何分析建立雾图对应无雾图像暗通道图的平面扇形模型,然后设定一种新型的高斯均值函数,对其标准差进行自适应处理,用以估计扇形模型的上下边界值,通过引入均值不等关系对两侧边界进行逼近,拟合出最优无雾图像暗通道图,进一步求得最佳透射率,同时也改进局部大气光的探索方法并复原出最终结果。实验表明,与其它一些经典算法相比较,所提算法能广泛适用于各类图像,去雾程度彻底且效果清晰自然,具有较低的时间复杂度,有利于实时处理。

  • 图  1  3个向量的几何表示

    图  2  各个向量间的匹配关系

    图  3  高斯均值函数

    图  4  透射率及效果对比图

    图  5  大气光值及效果对比图

    图  6  去雾示意图

    图  7  本文算法原理框图

    图  8  近景组图像(图像1-图像3)

    图  9  远近景交替组图像(图像4-图像6)

    图  10  远景组图像(图像7-图像8)

    表  1  改进的大气光探索方法

     输入:有雾图像${{I}^c}(x)$;
     步骤 1 找出有雾图像的3颜色通道的最大值${A}_{\max }^c(x) = \mathop {\max }\limits_{c \in \{\rm r,g,b\} } {{I}^c}(x)$
     步骤 2 进行形态学闭操作,滤波核尺寸分别为${r_1} = \min [w,h]/5$, ${r_2} = \min [w,h]/20$,得到两次闭操作结果${s_1}$和${s_2}$;
     步骤 3 求取两次闭操作的平均值,$s = ({s_1} + {s_2})/2$ ;
     步骤 4 进行交叉滤波平滑处理,得到最后的结果${{A}^c}$。
    下载: 导出CSV

    表  2  各个算法的$e$$r$指标对比

    图像He[9]算法Meng[11]算法Ren[13]算法Cai[12]算法Sun[16]算法本文算法
    erererererer
    14.501.285.821.797.551.472.761.086.441.229.011.41
    28.441.695.362.4820.711.5217.871.5615.741.4918.681.81
    313.891.7022.562.5910.821.979.111.4711.222.0121.832.01
    410.831.4824.933.7727.003.019.871.3612.741.9922.632.22
    56.871.2812.121.6915.611.7611.101.2817.252.0617.181.64
    626.231.7331.111.9031.362.6018.851.3022.751.9430.042.38
    715.511.8538.034.1220.352.5514.531.6324.742.9818.472.95
    83.691.413.121.588.941.792.491.136.331.748.561.42
    均值11.241.5517.882.4917.792.0811.821.3514.651.9318.301.98
    下载: 导出CSV

    表  3  各个算法的$\theta $$T(s)$指标对比

    图像He[9]算法Meng[11]算法Ren[13]算法Cai[12]算法Sun[16]算法本文算法
    $\theta $T$\theta $T$\theta $T$\theta $T$\theta $T$\theta $T
    10.000182.510.006513.8004.270.009313.010.003472.470.000012.65
    20.000222.560.003553.1603.0502.870.000192.670.000012.04
    30.000312.380.000663.0803.780.001972.940.001622.0102.06
    402.610.000034.5404.600.001262.980.002762.3902.07
    50.000362.460.000043.500.000132.6704.0102.0002.07
    60.001612.8004.4003.360.001183.680.000192.1702.09
    70.000093.020.000145.1003.2203.3102.5702.43
    80.002943.940.000796.550.000183.340.001697.340.000242.770.000162.55
    均值0.000712.780.001464.270.000033.530.001923.770.001052.380.000022.25
    下载: 导出CSV
  • 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. doi: 10.3788/OPE.20142208.2214

    ZHOU Yan, LI Qingwu, and HUO Guanying. Adaptive image enhancement based on NSCT coefficient histogram matching[J]. Optics and Precision Engineering, 2014, 22(8): 2214–2222. doi: 10.3788/OPE.20142208.2214
    CHEN Yang, LI Dan, and ZHANG Jianqiu. Complementary color wavelet: A novel tool for the color image/video analysis and processing[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2019, 29(1): 12–27. doi: 10.1109/TCSVT.2017.2776239
    刘海波, 杨杰, 吴正平, 等. 基于暗通道先验和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. doi: 10.16383/j.aas.2015.c140748

    LIU Haibo, YANG Jie, WU Zhengping, 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. doi: 10.16383/j.aas.2015.c140748
    SCHECHNER Y Y, NARASIMHAN S G, and NAYAR S K. Polarization-based vision through haze[J]. Applied Optics, 2003, 42(3): 511–525. doi: 10.1364/AO.42.000511
    NARASIMHAN S G and NAYAR S K. Interactive (de) weathering of an image using physical models[C]. 2003 IEEE Workshop on Color and Photometric Methods in Computer Vision, Nice, France, 2003: 1–8.
    TAN R T. Visibility in bad weather from a single image[C]. 2008 IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, USA, 2008: 1–8. doi: 10.1109/CVPR.2008.4587643.
    FATTAL R. Single image dehazing[J]. ACM Transactions on Graphics, 2008, 27(3): 72. doi: 10.1145/1360612.1360671
    TAREL J P and HAUTIÈRE N. Fast visibility restoration from a single color or gray level image[C]. The 12th IEEE International Conference on Computer Vision, Kyoto, Japan, 2009: 2201–2208.
    HE Kaiming, SUN Jian, and TANG Xiaoou. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341–2353. doi: 10.1109/TPAMI.2010.168
    ZHU Qingsong, MAI Jiaming, and SHAO Ling. A fast single image haze removal algorithm using color attenuation prior[J]. IEEE Transactions on Image Processing, 2015, 24(11): 3522–3533. doi: 10.1109/TIP.2015.2446191
    MENG Gaofeng, WANG Ying, DUAN Jiangyong, et al. Efficient image dehazing with boundary constraint and contextual regularization[C]. 2013 IEEE International Conference on Computer Vision, Sydney, Australia, 2013: 617–624.
    CAI Bolun, XU Xiangmin, JIA Kui, et al. DehazeNet: An end-to-end system for single image haze removal[J]. IEEE Transactions on Image Processing, 2016, 25(11): 5187–5198. doi: 10.1109/TIP.2016.2598681
    REN Wenqi, LIU Si, ZHANG Hua, et al. Single image dehazing via multi-scale convolutional neural networks[C]. The 14th European Conference on Computer Vision, Amsterdam, The Netherlands, 2016: 154–169.
    江巨浪, 孙伟, 王振东, 等. 基于透射率权值因子的雾天图像融合增强算法[J]. 电子与信息学报, 2018, 40(10): 2388–2394. doi: 10.11999/JEIT171032

    JIANG Julang, SUN Wei, WANG Zhendong, et al. Integrated enhancement algorithm for hazy image using transmittance as weighting factor[J]. Journal of Electronics &Information Technology, 2018, 40(10): 2388–2394. doi: 10.11999/JEIT171032
    HE Kaiming, SUN Jian, and TANG Xiaoou. Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6): 1397–1409. doi: 10.1109/TPAMI.2012.213
    SUN Wei, WANG Hao, SUN Changhao, et al. Fast single image haze removal via local atmospheric light veil estimation[J]. Computers & Electrical Engineering, 2015, 46: 371–383. doi: 10.1016/j.compeleceng.2015.02.009
    MIN Xiongkuo, ZHAI Guangtao, GU Ke, et al. Objective quality evaluation of dehazed images[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(8): 2879–2892. doi: 10.1109/TITS.2018.2868771
    杨爱萍, 王南, 庞彦伟, 等. 人工光源条件下夜间雾天图像建模及去雾[J]. 电子与信息学报, 2018, 40(6): 1330–1337. doi: 10.11999/JEIT170704

    YANG Aiping, WANG Nan, PANG Yanwei, et al. Nighttime haze removal based on new imaging model with artificial light sources[J]. Journal of Electronics &Information Technology, 2018, 40(6): 1330–1337. doi: 10.11999/JEIT170704
  • 加载中
图(10) / 表(3)
计量
  • 文章访问数:  2303
  • HTML全文浏览量:  839
  • PDF下载量:  114
  • 被引次数: 0
出版历程
  • 收稿日期:  2019-05-22
  • 修回日期:  2019-10-29
  • 网络出版日期:  2019-11-12
  • 刊出日期:  2020-03-19

目录

    /

    返回文章
    返回