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

基于多尺度小波U型网络的低光照图像增强

马璐

马璐. 基于多尺度小波U型网络的低光照图像增强[J]. 红外技术, 2022, 44(4): 410-420.
引用本文: 马璐. 基于多尺度小波U型网络的低光照图像增强[J]. 红外技术, 2022, 44(4): 410-420.
MA Lu. Low-light Image Enhancement Based on Multi-scale Wavelet U-Net[J]. Infrared Technology , 2022, 44(4): 410-420.
Citation: MA Lu. Low-light Image Enhancement Based on Multi-scale Wavelet U-Net[J]. Infrared Technology , 2022, 44(4): 410-420.

基于多尺度小波U型网络的低光照图像增强

基金项目: 

安徽省教育厅自然科学研究重点项目 KJ2020A0969

详细信息
    作者简介:

    马璐(1979-),男,硕士,副教授,主要研究计算机科学与技术、数字图像处理以及信息与控制。E-mail:ml_2021@126.com

  • 中图分类号: TP391.4

Low-light Image Enhancement Based on Multi-scale Wavelet U-Net

  • 摘要: 成像系统实时采集的低光照环境图像具有照度低、噪声严重、视觉效果差等问题,为了提高低光照环境成像质量,本文提出基于多尺度小波U型网络的低光照图像增强方法。该方法采用多级编解码器构建U型网络,并引入小波变换构建特征分频单元,分离高频和低频信息,增强对低频照度特征和高频纹理信息的感知。设计多尺度感知损失函数,指导网络学习低频信息到高频信息的逐级重建,从而优化网络的收敛和性能。最后,在LOL、LIME、NPE、MEF、DICM和VV数据集上进行测试。实验结果表明,所提方法能够有效提升图像照度,抑制图像噪声和纹理丢失问题,并在PSNR、SSIM、LOE和NIQE评价指标上均优于比较算法,在主观和客观评价方面均优于其他对比算法。
  • 图  1  多尺度小波U型网络结构

    Figure  1.  The architecture of multi-scale wavelet U-shaped network

    图  2  基于特征分频的编码器(左)和解码器(右)

    Figure  2.  Encoder (left) and decoder (right) based on frequency decomposition of features

    图  3  Pixel Shuffle和逆Pixel Shuffle方法示意图

    Figure  3.  Schematic diagram of Pixel Shuffle and inverse Pixel Shuffle method

    图  4  多尺度感知损失示意图

    Figure  4.  Schematic diagram of multi-scale perceived loss

    图  5  LOL数据集的单张图像客观评价结果

    Figure  5.  Objective evaluation results of single image in LOL dataset

    图  6  不同方法在多个数据集上的图像增强结果

    Figure  6.  Image enhancement results of different methods on multiple datasets

    图  7  LOL数据集中的146.jpg图像增强结果:

    (a) Low; (b) BPDHE; (c) LIME; (d) MF; (e) Retinexnet; (f) BIMEF; (g) KinD; (h) Ours

    Figure  7.  Enhancement results of "146.jpg" in LOL dataset:

    (a) Low; (b) BPDHE; (c) LIME; (d) MF; (e) Retinexnet; (f) BIMEF; (g) KinD; (h) Ours

    图  8  VV数据集中的P1020044.jpg图像增强结果:

    (a) Low; (b) BPDHE; (c) LIME; (d) MF; (e) Retinexnet; (f) BIMEF; (g) KinD; (h) Ours

    Figure  8.  Enhancement results of "p1020044.jpg" in VV dataset:

    (a) Low; (b) BPDHE; (c) LIME; (d) MF; (e) Retinexnet; (f) BIMEF; (g) KinD; (h) Ours

    图  9  LIME数据集10.bmp图像增强结果:

    (a) Low; (b) BPDHE; (c) LIME; (d) MF; (e) Retinexnet; (f) BIMEF; (g) KinD; (h) Ours

    Figure  9.  Enhancement results of "10.bmp" in LIME dataset:

    (a) Low; (b) BPDHE; (c) LIME; (d) MF; (e) Retinexnet; (f) BIMEF; (g) KinD; (h) Ours

    图  10  四种不同组合配置的网络训练过程

    Figure  10.  Training process of 4 networks with different configurations

    图  11  真实低光照图像增强结果:其中(a)和(b)为夜晚场景,(c)和(d)为阴雨天场景,(e)和(f)为早晨或傍晚场景

    Figure  11.  The results of real low-light image enhancement, where (a) and (b) are night scenes, (c) and (d) are overcast and rainy scenes, and (e) and (f) are morning or evening scenes

    表  1  不同低光照增强算法在LOL数据集上的结果

    Table  1.   Results of different low light enhancement algorithms on LOL dataset

    Metrics Low BPDHE LIME MF Retinexnet BIMEF KinD Ours
    PSNR 7.8666 11.8748 16.9332 16.9332 16.9816 13.9722 20.5955 24.5499
    SSIM 0.1259 0.3415 0.5644 0.6048 0.5594 0.5771 0.8045 0.8913
    LOE 1417.1 1772.8 3207.6 1721.2 4244.1 1553.3 1795.3 1267.1
    NIQE 6.7483 7.9852 8.3777 8.8855 8.8779 7.5029 5.3561 5.4289
    下载: 导出CSV

    表  2  不同网络的编/解码器和损失函数的配置

    Table  2.   Configuration of codecs and loss function for different networks

    Combination Single-scale L1 Multi-scale L1 Cascaded residual blocks FDF
    N1 - -
    N2 - -
    N3 - -
    N4 - -
    下载: 导出CSV

    表  3  不同组合网络的性能比较

    Table  3.   Performance comparison of different combination networks

    Datasets LOL LIME NPE MEF DICM VV Average
    N1 6.8072 5.0207 6.4623 6.3248 6.5652 6.1562 6.2227
    N2 4.8663 4.3757 5.3071 5.4867 5.0311 4.9305 4.9996
    N3 4.8091 4.2395 6.2099 6.6436 6.0698 5.8492 5.6369
    N4 4.6112 4.2251 4.9695 5.4682 4.9888 4.7840 4.8411
    下载: 导出CSV
  • [1] 王萌萌, 彭敦陆. Retinex-ADNet: 一个低光照图像增强系统[J]. 小型微型计算机系统, 2022, 43(2): 367-371 https://www.cnki.com.cn/Article/CJFDTOTAL-XXWX202202021.htm

    WANG M M, PENG D L. Retinex-ADNet: a low-light image enhancement system[J]. Journal of Chinese Computer Systems, 2022, 43(2): 367-371. https://www.cnki.com.cn/Article/CJFDTOTAL-XXWX202202021.htm
    [2] 蒋一纯, 詹伟达, 朱德鹏. 基于亮度通道细节增强的低照度图像处理[J]. 激光与光电子学进展, 2021, 58(4): 83-91. https://www.cnki.com.cn/Article/CJFDTOTAL-JGDJ202104011.htm

    JIANG Y C, ZHAN W D, ZHU D P. Low-illuminance image processing based on brightness channel detail enhancement[J]. Laser & Optoelectronics Progress, 2021, 58(4): 83-91. https://www.cnki.com.cn/Article/CJFDTOTAL-JGDJ202104011.htm
    [3] 黄慧, 董林鹭, 刘小芳, 等. 改进Retinex的低光照图像增强[J]. 光学精密工程, 2020, 28(8): 1835-1849. https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM202008022.htm

    HUANG H, DONG L L, LIU X F, et al. Improved Retinex low light image enhancement method[J]. Optics and Precision Engineering, 2020, 28(8): 1835-1849. https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM202008022.htm
    [4] Ibrahim H, Pik Kong N S. Brightness preserving dynamic histogram equalization for image contrast enhancement[J]. IEEE Transactions on Consumer Electronics, 2007, 53(4): 1752-1758. doi:  10.1109/TCE.2007.4429280
    [5] Jobson D J, Rahman Z, Woodell G A. Properties and performance of a center/surround retinex[J]. IEEE Transactions on Image Processing , 1997, 6(3): 451-62. doi:  10.1109/83.557356
    [6] Jobson D J, Rahman Z, Woodell G A. A multiscale Retinex for bridging the gap between color images and the human observation of scenes[J]. IEEE Transactions on Image Processing, 1997, 6(7): 965-976. doi:  10.1109/83.597272
    [7] GAO Y, HU H M, LI B, et al. Naturalness preserved nonuniform illumination estimation for image enhancement based on Retinex[J]. IEEE Transactions on Multimedia, 2018, 20(2): 335-344. doi:  10.1109/TMM.2017.2740025
    [8] FU X Y, ZENG D L, HUANG Y, et al. A fusion-based enhancing method for weakly illuminated images[J]. Signal Processing, 2016, 129: 82-96. doi:  10.1016/j.sigpro.2016.05.031
    [9] 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
    [10] Kin G L, Adedotun A, Soumik S. LLNet: A deep autoencoder approach to natural low-light image enhancement[J]. Pattern Recognition, 2017, 61: 650-662. doi:  10.1016/j.patcog.2016.06.008
    [11] SHEN L, YUE Z, FENG F, et al. MSR-net: low-light image enhancement using deep convolutional network[EB/OL]. [2017-11-07]. https://arxiv.org/abs/1711.02488.
    [12] WEI C, WANG W, YANG W, et al. Deep Retinex decomposition for low-light enhancement[C]//Proceedings of 2018 British Machine Vision Conference on Machine Vision, Image Processing, and Pattern Recognition, 2018: 1-12(DOI: 10.48550/ARXIV.1808.04560).
    [13] HU J, SHEN L, Albanie S, SUN G, et al. Squeeze-and-excitation networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8): 2011-2023. doi:  10.1109/TPAMI.2019.2913372
    [14] SHI W, Caballero J, Huszár F, et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016: 1874-1883.
    [15] Lim B, Son S, Kim H, et al. Enhanced deep residual networks for single image super-resolution[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops(CVPRW), 2017: 1132-1140.
    [16] Ledig C, Theis L, Huszar F, et al. Photo-realistic single image super-resolution using a generative adversarial network[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017: 105-114.
    [17] MA K, ZENG K, WANG Z. Perceptual quality assessment for multi-exposure image fusion[J]. IEEE Transactions on Image Processing, 2015, 24(11): 3345-3356. doi:  10.1109/TIP.2015.2442920
    [18] LEE C W, LEE C, KIM C S. Contrast enhancement based on layered difference representation of 2D histograms[J]. IEEE Transactions on Image Processing, 2013, 22(12): 5372-5384. doi:  10.1109/TIP.2013.2284059
    [19] WANG S, 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
    [20] Mittal A, Soundararajan R, Bovik A C. Making a "completely blind" image quality analyzer[J]. IEEE Signal Processing Letters, 2013, 20(3): 209-212. doi:  10.1109/LSP.2012.2227726
    [21] FU X, ZENG D, HUANG Y, et al. A fusion-based enhancing method for weakly illuminated images[J]. Signal Processing, 2016, 129: 82-96.
    [22] YING Z, LI G, GAO W. A bio-inspired multi-exposure fusion framework for low-light image enhancement[EB/OL]. [2017-11-02]. https://arxiv.org/abs/1711.00591.
    [23] ZHANG Y, ZHANG J, GUO X. Kindling the darkness: a practical low-light image enhancer[C]//Proceedings of The 27th ACM International Conference on Multimedia, 2019: 1632-1640.
  • 加载中
图(11) / 表(3)
计量
  • 文章访问数:  150
  • HTML全文浏览量:  39
  • PDF下载量:  37
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-05-19
  • 修回日期:  2021-06-14
  • 刊出日期:  2022-04-20

目录

    /

    返回文章
    返回