基于机器视觉的公路交通标志自动化巡检系统

PDF(1828 KB)

交通运输研究 ›› 2018, Vol. 4 ›› Issue (5) : 71-76.

安全与环保

基于机器视觉的公路交通标志自动化巡检系统

申雷霄,刘军

作者信息 +

Road Traffic Sign Automatic Inspection System Based on Machine Vision

SHEN Lei-xiao and LIU Jun

Author information +

文章历史 +

摘要

针对既有交通标志巡检的调查手段和分析方法存在的成本高、效率低、精度低的弊端，提出了一种基于机器视觉的公路交通标志自动化巡检系统，实现对公路交通标志的移动式实时检测与分析。首先利用YOLO （You Only Look Once）算法，将机器视觉技术运用到交通标志的检测中，加快了检测速度。然后给出了交通标志自动化巡检系统的系统构架、系统结构与功能及数据管理方案。最后利用该系统进行实测。实测结果显示，该自动化巡检系统能够准确地检测交通标志、道路标线及路面坑塘，具有较高的测试精度及较好的测试效果。

Abstract

To avoid the drawbacks such as high cost, low efficiency, and low precision of the survey means and analysis methods of traditional traffic sign inspection system, an automatic inspection system was proposed based on machine vision to realize the mobile real-time detection and analysis of highway traffic signs. Firstly, based on the YOLO (You Only Look Once) algorithm, the application of machine vision technology in detecting traffic signs was realized, which speeded up the detection. Secondly, the design of system architecture, system structure and function, and data management scheme of the traffic sign automatic inspection system were given detailedly. Finally, the actual measurement experiment was carried out using the proposed system and the measured results of the system were obtained. The results shows that this automatic inspection system can accurately detect traffic signs, road markings and pavement pits with high accuracy and approving effect.

导出引用

申雷霄, 刘军. 基于机器视觉的公路交通标志自动化巡检系统[J]. 交通运输研究. 2018, 4(5): 71-76

SHEN Lei-xiao and LIU Jun. Road Traffic Sign Automatic Inspection System Based on Machine Vision[J]. Transport Research. 2018, 4(5): 71-76

参考文献

[1] 安泰. 信息化管理在公路交通标志管理上的应用[EB/OL]. (2013-08-03)[2018-09-05]. [2] 高霞. 浅析高速公路交通安全设施养护维修体会[J]. 科技视界，2018（8）： 224-225. [3] KUO W J, LIN C C. Two-Stage Road Sign Detection and Recognition[C]// IEEE. Proceedings of 2007 IEEE International Conference on Multimedia and Expo. Beijing: IEEE, 2007: 1427-1430. [4] CIRESAN D, MEIER U, MASCI J, et al. A Committee of Neural Networks for Traffic Sign Classification[C]// IEEE. Proceedings of 2011 International Joint Conference on Neural Networks. San Jose, USA: IEEE, 2011: 1918-1921. [5] SERMANET P, LECUN Y. Traffic Sign Recognition with Multi- scale Convolutional Networks[C]// IEEE. Proceedings of International Joint Conference on Neural Networks. San Francisco , USA: IEEE, 2011: 2809-2813. [6] SHOPA P, SUMITHA N, PATRA P S K. Traffic Sign Detection and Recognition Using OpenCV[C]// IEEE. Proceedings of International Conference on Information Communication and Embedded Systems. Chennai, India: IEEE, 2015: 1-6. [7] 刘成云，常发亮，陈振学. 基于感兴趣区域和HOGMBLBP特征的交通标识检测[J]. 电子与信息学报，2016，38（5）：1092-1098. [8] QIAN R Q, ZHANG B L, YUE Y, et al. Robust Chinese Traffic Sign Detection and Recognition with Deep Convolutional Neural Network[C]// IEEE. Proceedings of International Conference on Natural Computation. Zhangjiajie, China: IEEE, 2016: 791-796. [9] ÁLVARO A G, SOILAN M, ÁLVAREZ-GARCIA J A, et al. Exploiting Synergies of Mobile Mapping Sensors and Deep Learning for Traffic Sign Recognition Systems[J]. Expert Systems with Applications, 2017, 89: 286-295. [10] 武林秀，李厚杰，贺建军，等. 基于深度学习的交通标志检测方法研究[J]. 大连民族大学学报， 2018（5）：460-463. [11] 任洪梅. 基于深度学习的路面交通标志识别[J]. 信息通信，2017（4）：26-27. [12] 王方石，王坚，李兵，等. 基于深度属性学习的交通标志检测[J]. 吉林大学学报（工学版），2018，48（1）：319-329. [13] REDMON J, DIVVALA S, GIRSHICK R, et al. You Only Look Once: Unified, Real- Time Object Detection[C]// IEEE. Proceedings of 2016 IEEE Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE, 2016: 779-788. [14] 王宇宁，庞智恒，袁德明. 基于YOLO算法的车辆实时检测[J]. 武汉理工大学学报，2016，38（10）：41-46. [15] 王霖郁，蒋强卫，李爽. 基于双目图像多特征点融合匹配物体识别与定位研究[J]. 无线电工程， 2018（8）：628-633.