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。
    Abstract: The real-time images collected by imaging systems in low illumination environments suffer from low illumination, severe noise and poor visual effects. To improve the image quality in low light environments, this study proposes a low-light image enhancement method based on a multi-scale wavelet U-Net. This method uses multi-level encoders and decoders to construct a U-Net and introduces the wavelet transform to develop a unit for frequency decomposition of features. This improves the perception of illumination and texture by separating high-frequency and low-frequency information. Multi-scale perceived loss is designed to guide the learned mapping of step-by-step reconstruction from low-frequency information to high-frequency information, thereby optimizing the convergence and performance of the network. Finally, the proposed method and comparison methods are tested on the LOL, LIME, NPE, MEF, DICM and VV datasets. The experimental results demonstrate that the proposed method can effectively brighten images, suppress image noise and texture loss, and improve the PSNR, SSIM, LOE and NIQE metrics. The proposed method exhibits better performance than other comparison algorithms in subjective and objective evaluation.
  • 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.

  • 期刊类型引用(18)

    1. 刘传洋,吴一全. 基于红外图像的电力设备识别及发热故障诊断方法研究进展. 中国电机工程学报. 2025(06): 2171-2196 . 百度学术
    2. 刘垚. 复合绝缘子表面异常发热点识别方法. 光通信研究. 2024(06): 42-47 . 百度学术
    3. 戴月明,杨陆锋,童雄敏. 基于红外图像与深度学习的EMS低压设备实时断面状态校核方法. 红外技术. 2024(12): 1464-1470 . 本站查看
    4. 刘宸轩. 基于小波分析的电气设备故障检测方法研究. 专用汽车. 2023(01): 58-60 . 百度学术
    5. 张宗包. 基于图像融合技术的变电站二次设备热故障自主定位研究. 机械与电子. 2023(03): 18-22 . 百度学术
    6. 魏岸若. 基于数据驱动的电气自动化设备运行故障预警研究. 电气技术与经济. 2023(06): 71-74+89 . 百度学术
    7. 林航,方宁. 模糊聚类算法在舰船电气系统故障远程检测中的应用. 舰船科学技术. 2022(04): 156-160 . 百度学术
    8. 常硕,梁杰,姜久超. 基于模拟退火算法的水电站电气装置故障运行状态自动捕捉方法. 水利水电技术(中英文). 2022(03): 110-118 . 百度学术
    9. 杨琳玮. 基于物联网技术的电气设备全生命周期风险预测方法. 自动化技术与应用. 2022(06): 73-76 . 百度学术
    10. 葛黄徐,郑雷,江洪,郭一凡,周东国. 基于MST框架的PCNN输电线路红外热故障区域提取方法. 红外技术. 2022(07): 709-715 . 本站查看
    11. 邵健. 基于无线传感网络的建筑电气设备自动监测系统. 能源与环保. 2022(08): 251-256 . 百度学术
    12. 刘俊,章磊. 基于半导体激光干涉技术的电气设备状态检测研究. 激光杂志. 2021(05): 52-56 . 百度学术
    13. 王子默,王清亮. 基于梯度扩散的电气设备调试故障行波检测. 计算机仿真. 2020(05): 468-472 . 百度学术
    14. 邹梓秀. 一种基于MeanShift改进的移动目标跟踪算法. 九江学院学报(自然科学版). 2020(01): 45-47 . 百度学术
    15. 张平,李东民,苏晓宇,李冠群,朱光南. SIFT特征点匹配算法在GIS设备内部发热判断中的应用. 自动化与仪器仪表. 2020(07): 190-193+197 . 百度学术
    16. 许晓路,周文,周东国,朱诗沁,倪辉,罗传仙. 基于PCNN分层聚类迭代的故障区域自动提取方法. 红外技术. 2020(08): 809-814 . 本站查看
    17. 王琦,张永杰,周竞,刘庸奇. 基于无线红外热成像仪的变电设备识别和检测. 微型电脑应用. 2020(09): 170-172+176 . 百度学术
    18. 徐小冰,袁婧,廖雁群,韦亦龙,周承科,周文俊. 基于Faster RCNN与Mean-Shift的电缆附件缺陷红外图像自动诊断方法. 高电压技术. 2020(09): 3070-3080 . 百度学术

    其他类型引用(6)

图(11)  /  表(3)
计量
  • 文章访问数:  219
  • HTML全文浏览量:  79
  • PDF下载量:  49
  • 被引次数: 24
出版历程
  • 收稿日期:  2021-05-18
  • 修回日期:  2021-06-13
  • 刊出日期:  2022-04-19

目录

    /

    返回文章
    返回