• 《工程索引》(EI)刊源期刊
  • 综合性科学技术类中文核心期刊
  • 中国科技论文统计源期刊
  • 中国科学引文数据库来源期刊

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

弱光照条件下交通标志检测与识别

赵坤 刘立 孟宇 孙若灿

赵坤, 刘立, 孟宇, 孙若灿. 弱光照条件下交通标志检测与识别[J]. 工程科学学报, 2020, 42(8): 1074-1084. doi: 10.13374/j.issn2095-9389.2019.08.14.003
引用本文: 赵坤, 刘立, 孟宇, 孙若灿. 弱光照条件下交通标志检测与识别[J]. 工程科学学报, 2020, 42(8): 1074-1084. doi: 10.13374/j.issn2095-9389.2019.08.14.003
ZHAO Kun, LIU Li, MENG Yu, SUN Ruo-can. Traffic signs detection and recognition under low-illumination conditions[J]. Chinese Journal of Engineering, 2020, 42(8): 1074-1084. doi: 10.13374/j.issn2095-9389.2019.08.14.003
Citation: ZHAO Kun, LIU Li, MENG Yu, SUN Ruo-can. Traffic signs detection and recognition under low-illumination conditions[J]. Chinese Journal of Engineering, 2020, 42(8): 1074-1084. doi: 10.13374/j.issn2095-9389.2019.08.14.003

弱光照条件下交通标志检测与识别

doi: 10.13374/j.issn2095-9389.2019.08.14.003
基金项目: 国家重点研发计划资助项目(2018YFE0192900,2018YFC0810500,2018YFC0604403);国家高技术研究发展计划资助项目(2011AA060408);中央高校基本科研业务费专项资金资助项目(FRF-TP-17-010A2)
详细信息
    通讯作者:

    E-mail:myu@ustb.edu.cn

  • 中图分类号: TP391.4

Traffic signs detection and recognition under low-illumination conditions

More Information
  • 摘要: 针对弱光照条件下交通标志易发生漏检和定位不准的问题,本文提出了增强YOLOv3(You only look once)检测算法,一种实时自适应图像增强与优化YOLOv3网络结合的交通标志检测与识别方法。首先构建了大型复杂光照中国交通标志数据集;然后针对复杂的弱光照图像提出自适应增强算法,通过调整图像亮度和对比度强化交通标志与背景之间的差异;最后采用YOLOv3网络框架检测交通标志。为了降低先验锚点框设置精度以及图像中背景与前景比例严重失衡对检测精度造成的影响,优化了先验锚点框聚类算法和网络的损失函数。对比实验结果表明,在实时性大致相当的情况下,本文提出的增强YOLOv3检测算法较标准YOLOv3算法对交通标志有更高的回归精度和置信度,召回率和准确率分别提高0.96%和0.48%。
  • 图  1  不同天气及光照条件的图像样本. (a)阴天; (b)雨雪天; (c)光照充足; (d)光照不足

    Figure  1.  Image samples under different weather and illumination conditions: (a) overcast; (b) rain and snow; (c) sufficient illumination; (d) insufficient illumination

    图  2  交通标志数据分布示意图

    Figure  2.  Data distribution diagram for traffic signs

    图  3  自适应Gamma校正流程图

    Figure  3.  Flow diagram of adaptive gamma correction

    图  4  聚类中心数目测试结果

    Figure  4.  Test results of number for cluster centers

    图  5  优化前后损失值示意图

    Figure  5.  Loss value before and after optimization

    图  6  网络参数图

    Figure  6.  Network parameter diagram

    图  7  整体光照不足的图像. (a)图像处理前;(b)图像处理后;(c)图像处理前的像素概率直方图;(d)图像处理后的像素概率直方图

    Figure  7.  Images with low overall illumination: (a) image before processing; (b) image after processing; (c) pixel probability histograms of image before processing; (d) pixel probability histograms of image after processing

    图  9  光照充足图像。(a)图像处理前;(b)图像处理后;(c)图像处理前像素概率直方图;(d)图像处理后像素概率直方图

    Figure  9.  Images with sufficient illumination: (a) image before processing; (b) image after processing; (c) pixel probability histograms of image before processing; (d) pixel probability histograms of image after processing

    图  8  局部光照不足图像。(a)图像处理前;(b)图像处理后;(c)图像处理前像素概率直方图;(d)图像处理后像素概率直方图

    Figure  8.  Images with low local illumination: (a) image before processing; (b) image after processing; (c) pixel probability histograms of image before processing; (d) pixel probability histograms of image after processing

    图  10  不同算法测试结果可视化对比. (a, b)标准YOLOv3;(c, d)改进YOLOv3

    Figure  10.  Visual comparison of different algorithm for test results: (a, b) standard YOLOv3; (c, d) improved YOLOv3

    图  11  不同算法测试结果可视化对比。(a, b)标准YOLOv3;(c, d)增强YOLOv3

    Figure  11.  Visual comparison of different algorithms for test results: (a, b) standard YOLOv3; (c, d) enhanced YOLOv3

    表  1  图像分类

    Table  1.   Image classification

    Contrast categoryIntensity mean, λImage category
    IL≥ 0.5Low contrast and high brightness
    < 0.5Low contrast and low brightness
    IH≥ 0.5High contrast and high brightness
    < 0.5High contrast and low brightness
    下载: 导出CSV

    表  2  在LISA数据集上的测试结果(阈值=0.8,IOU=0.7)

    Table  2.   Test results on LISA dataset (threshold = 0.8, IOU = 0.7)

    AlgorithmNumber of traffic signsRecall/%Accuracy/%
    Standard YOLOv3144688.8099.07
    Improved YOLOv3144691.3698.44
    下载: 导出CSV

    表  3  在弱光照交通标志数据集上的测试结果(阈值=0.8,IOU=0.7)

    Table  3.   Test results on weak illumination traffic signs dataset (threshold = 0.8, IOU = 0.7)

    AlgorithmDark images with 2163 traffic signsBright images with 2315 traffic signsAll images with 4478 traffic signsRun time/ms
    Recall/%Accuracy/%Recall/%Accuracy/%Recall/%Accuracy/%
    Standard YOLOv3 96.30 98.91 98.49 99.30 97.43 99.11 33
    Enhanced YOLOv3 98.06 99.44 98.70 99.74 98.39 99.59 36
    下载: 导出CSV
  • [1] 张新钰, 高洪波, 赵建辉, 等. 基于深度学习的自动驾驶技术综述. 清华大学学报: 自然科学版, 2018, 58(4):438

    Zhang X Y, Gao H B, Zhao J H, et al. Overview of deep learning intelligent driving methods. <italic>J Tsinghua Univ Sci Technol</italic>, 2018, 58(4): 438
    [2] Salti S, Petrelli A, Tombari F, et al. Traffic sign detection via interest region extraction. <italic>Pattern Recognit</italic>, 2015, 48(4): 1039 doi: 10.1016/j.patcog.2014.05.017
    [3] Eichner M L, Breckon T P. Integrated speed limit detection and recognition from real-time video // 2008 IEEE Intelligent Vehicles Symposium. Eindhoven, 2008: 626
    [4] Lorsakul A, Suthakorn J. Traffic sign recognition using neural network on opencv: toward intelligent vehicle/driver assistance system. <italic>Intell Service Rob</italic>, 2007: 1
    [5] Barnes N, Zelinsky A. Real-time radial symmetry for speed sign detection // IEEE Intelligent Vehicles Symposium. Parma, 2004: 566
    [6] Loy G, Barnes N. Fast shape-based road sign detection for a driver assistance system // 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Sendai, 2004: 70
    [7] Maldonado-Bascon S, Lafuente-Arroyo S, Gil-Jimenez P, et al. Road-sign detection and recognition based on support vector machines. <italic>IEEE Trans Intell Transportation Syst</italic>, 2007, 8(2): 264 doi: 10.1109/TITS.2007.895311
    [8] Bahlmann C, Zhu Y, Ramesh V, et al. A system for traffic sign detection, tracking, and recognition using color, shape, and motion information // IEEE Proceedings. Intelligent Vehicles Symposium. Las Vegas, 2005: 255
    [9] Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation // 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, 2014: 580
    [10] Uijlings J R R, van de Sande K E A, Gevers T, et al. Selective search for object recognition. <italic>Int J Comput Vision</italic>, 2013, 104(2): 154 doi: 10.1007/s11263-013-0620-5
    [11] He K M, Zhang X Y, Ren S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition. <italic>IEEE Transactions Pattern Anal Mach Intell</italic>, 2015, 37(9): 1904 doi: 10.1109/TPAMI.2015.2389824
    [12] Girshick R. Fast R-CNN // 2015 IEEE International Conference on Computer Vision (ICCV). Santiago, 2015: 1440
    [13] Ren S Q, He K M, Girshick R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks. <italic>IEEE Transactions Pattern Anal Mach Intell</italic>, 2017, 39(6): 1137 doi: 10.1109/TPAMI.2016.2577031
    [14] Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object detection // 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, 2016: 779
    [15] Liu W, Anguelov D, Erhan D, et al. SSD: Single shot multibox detector // European Conference on Computer Vision. Amsterdam, 2016: 21
    [16] Ciresan D, Meier U, Masci J, et al. A committee of neural networks for traffic sign classification // The 2011 International Joint Conference on Neural Networks. San Jose, 2011: 1918
    [17] Sermanet P, LeCun Y. Traffic sign recognition with multi-scale convolutional networks // The 2011 International Joint Conference on Neural Networks. San Jose, 2011: 2809
    [18] Ciresan D, Meier U, Masci J, et al. Multi-column deep neural network for traffic sign classification. <italic>Neural Networks</italic>, 2012, 32: 333 doi: 10.1016/j.neunet.2012.02.023
    [19] Jin J Q, Fu K, Zhang C S. Traffic sign recognition with hinge loss trained convolutional neural networks. <italic>IEEE Trans-actions Intell Transportation Syst</italic>, 2014, 15(5): 1991 doi: 10.1109/TITS.2014.2308281
    [20] Mogelmose A, Trivedi M M, Moeslund T B. Vision-based traffic sign detection and analysis for intelligent driver assis-tance systems: perspectives and survey. <italic>IEEE Transactions Intell Transportation Syst</italic>, 2012, 13(4): 1484 doi: 10.1109/TITS.2012.2209421
    [21] Stallkamp J, Schlipsing M, Salmen J, et al. Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition. <italic>Neural Networks</italic>, 2012, 32: 323 doi: 10.1016/j.neunet.2012.02.016
    [22] Timofte R, Zimmermann K, Gool L V. Multi-view traffic sign detection, recognition, and 3D localization. <italic>Mach Vision Appl</italic>, 2014, 25(3): 633 doi: 10.1007/s00138-011-0391-3
    [23] 余超超. 交通标志检测与识别算法研究[学位论文]. 成都: 西南交通大学, 2017

    Yu C C. Research on Traffic Sign Detection and Recognition Algorithm[Dissertation]. Chengdu: Southwest Jiaotong University, 2017
    [24] Celik T, Tjahjadi T. Automatic image equalization and contrast enhancement using Gaussian mixture modeling. <italic>IEEE Trans Image Process</italic>, 2011, 21(1): 145
    [25] Redmon J, Farhadi A. YOLOv3: an Incremental Improvement[J/OL]. arXiv preprint (2018-04-08)[2019-08-14]. http://arxiv.org/abs/1804.02767
    [26] Redmon J, Farhadi A. YOLO9000: Better, faster, stronger // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, 2017: 6517
  • 加载中
图(11) / 表(3)
计量
  • 文章访问数:  918
  • HTML全文浏览量:  651
  • PDF下载量:  46
  • 被引次数: 0
出版历程
  • 收稿日期:  2019-08-14
  • 刊出日期:  2020-09-11

目录

    /

    返回文章
    返回