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

结合光源分割和线性图像深度估计的夜间图像去雾

吕建威 钱锋 韩昊男 张葆

吕建威, 钱锋, 韩昊男, 张葆. 结合光源分割和线性图像深度估计的夜间图像去雾[J]. 中国光学(中英文), 2022, 15(1): 34-44. doi: 10.37188/CO.2021-0114
引用本文: 吕建威, 钱锋, 韩昊男, 张葆. 结合光源分割和线性图像深度估计的夜间图像去雾[J]. 中国光学(中英文), 2022, 15(1): 34-44. doi: 10.37188/CO.2021-0114
LV Jian-wei, QIAN Feng, HAN Hao-nan, ZHANG Bao. Nighttime image dehazing with a new light segmentation method and a linear image depth estimation model[J]. Chinese Optics, 2022, 15(1): 34-44. doi: 10.37188/CO.2021-0114
Citation: LV Jian-wei, QIAN Feng, HAN Hao-nan, ZHANG Bao. Nighttime image dehazing with a new light segmentation method and a linear image depth estimation model[J]. Chinese Optics, 2022, 15(1): 34-44. doi: 10.37188/CO.2021-0114

结合光源分割和线性图像深度估计的夜间图像去雾

doi: 10.37188/CO.2021-0114
基金项目: 国家自然科学基金资助项目(No. 61705225)
详细信息
    作者简介:

    吕建威(1993—),男,辽宁大连人,博士研究生,2016年于大连理工大学获得理学学士学位,现为中国科学院长春光学精密机械与物理研究所博士研究生,主要从事计算机视觉和图像处理方面的研究。E-mail:lvjianwei@ciomp.ac.cn

    张 葆(1966—),男,吉林磐石人,中国科学院长春精密机械与物理研究所研究员。1989年获长春理工大学理学学士学位,1994年获长春理工大学理学硕士学位,2004年在中国科学院长春精密机械与物理研究所获得博士学位,2004年5月至8月,曾任澳大利亚悉尼大学、阿德莱德大学高级访问学者。主要研究方向:图像处理、光学设计、目标识别与跟踪。E-mail:zhangb@ciomp.ac.cn

  • 中图分类号: TP391.41

Nighttime image dehazing with a new light segmentation method and a linear image depth estimation model

Funds: Supported by National Natural Science Foundation of China (No. 61705225)
More Information
  • 摘要: 夜间有雾图像通常具有对比度低、光照不均匀、颜色偏移以及噪声较多等现象,这些退化现象使得夜间图像去雾具有极大的挑战性。针对夜间图像存在的退化问题,本文提出了一种能够在夜间图像中有效去雾并提高图像质量的方法。首先,将图像分解成光晕层和有雾层,并对有雾层进行颜色校正。其次,通过一种新提出的带有伽马变换的图像光源分割方法来分割光源,并设置分割阈值作为像素点属于光源区域的概率值。然后,将得到的概率值与最大反射先验相结合来估计光源和非光源区域的大气光值。最后,根据图像深度与亮度、饱和度以及梯度之间的关系建立线性模型,进一步估计透射率的值。实验得到的分割阈值为0.07,线性深度估计参数分别为1.0267、−0.5966、0.6735、0.004135。实验结果表明本文方法在夜间图像去雾、消除光晕、减少噪声,以及提高可视度方面取得良好的效果。

     

  • 图 1  夜间有雾图像模型

    Figure 1.  Image model for the scene with haze at night

    图 2  图像层分解和颜色变换过程图

    Figure 2.  Image layer decomposition and color transformation

    图 3  夜间有雾图像的光源分割结果

    Figure 3.  The results of nighttime hazy image segmentation

    图 4  夜间无雾图像和对应合成的夜间有雾图像

    Figure 4.  Nighttime haze-free images and the corresponding synthetic hazy images

    图 5  使用不同透射率的去雾结果

    Figure 5.  The dehazing results using different transmission

    图 6  本文方法与其他去雾方法效果的比较。从左到右各列分别为:原图,使用Zhang方法[13]、Li方法[14]、Yu方法[18]和本文方法获得的图像

    Figure 6.  Comparison of the effects of the proposed method with other methods. From left to right: original image, images obtained with Zhang’s method[13], Li’s method[14], Yu’s method[18] and proposed method

    图 7  夜间去雾方法效果比较

    Figure 7.  Comparison of nighttime dehazing algorithms

    表  1  图像质量评价数据表

    Table  1.   The values of image quality assessment

    Quality assessmentZhang et alLi et alYu et alOurs
    e26.744832.113423.259033.6594
    IVM8.05128.86467.239910.0275
    SSIM0.55570.72340.75200.7761
    CG0.38540.39910.31590.6566
    VCM43.666725.666756.000059.8333
    PSNR17.599420.210421.556021.8774
    下载: 导出CSV
  • [1] 刘坤, 毕笃彦, 王世平, 等. 基于稀疏特征提取的单幅图像去雾[J]. 光学学报,2018,38(3):0310001. doi: 10.3788/AOS201838.0310001

    LIU K, BI D Y, WANG SH P, et al. Single image dehazing based on sparse feature extraction[J]. Acta Optica Sinica, 2018, 38(3): 0310001. (in Chinese) doi: 10.3788/AOS201838.0310001
    [2] 韩昊男, 钱锋, 吕建威, 等. 改进暗通道先验的航空图像去雾[J]. 光学 精密工程,2020,28(6):1387-1394. doi: 10.3788/OPE.20202806.1387

    HAN H N, QIAN F, LV J W, et al. Aerial image dehazing using improved dark channel prior[J]. Optics and Precision Engineering, 2020, 28(6): 1387-1394. (in Chinese) doi: 10.3788/OPE.20202806.1387
    [3] 邓莉. 针对明亮区域的自适应全局暗原色先验去雾[J]. 光学 精密工程,2016,24(4):892-901. doi: 10.3788/OPE.20162404.0892

    DENG L. Adaptive image dehazing for bright areas based on global dark channel prior[J]. Optics and Precision Engineering, 2016, 24(4): 892-901. (in Chinese) doi: 10.3788/OPE.20162404.0892
    [4] ANCUTI C O, ANCUTI C, DE VLEESCHOUWER C, et al. Color channel transfer for image dehazing[J]. IEEE Signal Processing Letters, 2019, 26(9): 1413-1417. doi: 10.1109/LSP.2019.2932189
    [5] LI M D, LIU J Y, YANG W H, et al. Structure-revealing low-light image enhancement via robust retinex model[J]. IEEE Transactions on Image Processing, 2018, 27(6): 2828-2841. doi: 10.1109/TIP.2018.2810539
    [6] NARASIMHAN S G, NAYAR S K. Shedding light on the weather[C]. Proceedings of 2013 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE, 2003.
    [7] 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. doi: 10.1109/TPAMI.2010.168
    [8] TAN R T. Visibility in bad weather from a single image[C]. Proceedings of 2008 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 2008.
    [9] ANCUTI C O, ANCUTI C. Single image dehazing by multi-scale fusion[J]. IEEE Transactions on Image Processing, 2013, 22(8): 3271-3282. doi: 10.1109/TIP.2013.2262284
    [10] MENG G F, WANG Y, DUAN J Y. Efficient image dehazing with boundary constraint and contextual regularization[C]. Proceedings of 2013 IEEE International Conference on Computer Vision, IEEE, 2013.
    [11] GUO X J, LI Y, LING H B. LIME: low-light image enhancement via illumination map estimation[J]. IEEE Transactions on Image Processing, 2017, 26(2): 982-993. doi: 10.1109/TIP.2016.2639450
    [12] PEI S C, LEE T Y. Nighttime haze removal using color transfer pre-processing and dark channel prior[C]. Proceedings of 2012 19th IEEE International Conference on Image Processing, IEEE, 2012.
    [13] ZHANG J, CAO Y, WANG Z F. Nighttime haze removal based on a new imaging model[C]. Proceedings of 2014 IEEE International Conference on Image Processing, IEEE, 2014.
    [14] LI Y, TAN R T, BROWN M S. Nighttime haze removal with glow and multiple light colors[C]. Proceedings of 2015 IEEE International Conference on Computer Vision, IEEE, 2015.
    [15] LI Y, BROWN M S. Single image layer separation using relative smoothness[C]. Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 2014.
    [16] 杨爱萍, 白煌煌. 基于Retinex理论和暗通道先验的夜间图像去雾算法[J]. 激光与光电子学进展,2017,54(4):041002.

    YANG A P, BAI H H. Nighttime image defogging based on the theory of Retinex and dark channel prior[J]. Laser &Optoelectronics Progress, 2017, 54(4): 041002. (in Chinese)
    [17] ZHANG J, CAO Y, FANG SH, et al.. Fast haze removal for nighttime image using maximum reflectance prior[C]. Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 2017.
    [18] YU T, SONG K, MIAO P, et al. Nighttime single image dehazing via pixel-wise alpha blending[J]. IEEE Access, 2019, 7: 114619-114630. doi: 10.1109/ACCESS.2019.2936049
    [19] YANG M M, LIU J CH, LI ZH G. Superpixel-based single nighttime image haze removal[J]. IEEE Transactions on Multimedia, 2018, 20(11): 3008-3018. doi: 10.1109/TMM.2018.2820327
    [20] XU L, ZHENG SH CH, JIA J Y. Unnatural L0 sparse representation for natural image deblurring[C]. Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 2013.
    [21] BUCHSBAUM G. A spatial processor model for object colour perception[J]. Journal of the Franklin Institute, 1980, 310(1): 1-26. doi: 10.1016/0016-0032(80)90058-7
    [22] GAO C, WANG Z, XU Y, et al. The von kries chromatic adaptation transform and its generalization[J]. Chinese Optics Letters, 2020, 18131: 6.
    [23] LAND E H. The retinex theory of color vision[J]. Scientific American, 1978, 237(6): 108-128.
    [24] HE K M, SUN J, TANG X O. Guided image filtering[C]. Proceedings of the 11th European Conference on Computer Vision, Springer, 2010.
    [25] WANG SH H, ZHENG J, HU H M, et al. Naturalness preserved enhancement algorithm for non-uniform illumination images[J]. IEEE Transactions on Image Processing, 2013, 22(9): 3538-3548. doi: 10.1109/TIP.2013.2261309
    [26] ZHU Q S, MAI J M, SHAO L. 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
    [27] LOU W H, LI Y J, YANG G W, et al. Integrating haze density features for fast nighttime image dehazing[J]. IEEE Access, 2020, 8: 113318-113330. doi: 10.1109/ACCESS.2020.3003444
    [28] ANCUTI C, ANCUTI C O, DE VLEESCHOUWER C. D-HAZY: a dataset to evaluate quantitatively dehazing algorithms[C]. Proceedings of 2016 IEEE International Conference on Image Processing, IEEE, 2016.
    [29] MARQUARDT D W. An algorithm for least-squares estimation of nonlinear parameters[J]. Journal of the Society for Industrial and Applied Mathematics, 1963, 11(2): 431-441. doi: 10.1137/0111030
    [30] TRIPATHI A K, MUKHOPADHYAY S. Removal of fog from images: a review[J]. IETE Technical Review, 2012, 29(2): 148-156. doi: 10.4103/0256-4602.95386
  • 加载中
图(7) / 表(1)
计量
  • 文章访问数:  600
  • HTML全文浏览量:  320
  • PDF下载量:  83
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-05-24
  • 修回日期:  2021-06-18
  • 网络出版日期:  2021-09-09
  • 刊出日期:  2022-01-19

目录

    /

    返回文章
    返回