基于视频的轨道车辆自主定位方法研究
CSTR:
作者:
作者单位:

1.同济大学 上海市轨道交通结构耐久与系统安全重点实验室,上海 201804;2.清华大学 土木水利学院,北京 100084;3.中电建路桥集团有限公司,北京 100070;4.上海泽高电子工程技术股份有限公司,上海 201900

作者简介:

沈 拓,工程师,博士生,硕士生导师,主要研究方向为轨道交通控制与安全。E-mail:st8250@163.com

通讯作者:

盛 峰,教授级高级工程师,博士生,主要研究方向为土木水利工程、轨道交通控制。 E-mail: s18663726777f@126.com

中图分类号:

U239.5;TP391.41

基金项目:

国家重点研发计划(2022YFB4300501);上海市科委课题(23DZ2204900);校企战略性合作专项高速铁路绿色智能施工关键技术研究(kh0160020230946、LQKY2022-01-1)


Vision-Based Absolute Position Extraction Method for Rail Vehicles
Author:
Affiliation:

1.Shanghai Key Laboratory of Rail Infrastructure Durability and System Safety, Tongji University, Shanghai 201804, China;2.School of Civil Engineering, Tsinghua University, Beijing 100084, China;3.Powerchina Roadbridge Group Co., Ltd., Beijing 100070, China;4.Shanghai Zegao Electrical Engineering Technology Co., Ltd., Shanghai 201900, China

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [9]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    针对轨道施工车辆自主定位需求,提出一种基于车载前视相机拍摄百米标视频的轨道车辆自主定位方法。该方法首先对YOLOX-s网络进行改进并构建了百米标的目标检测模型,完成对百米标的目标检测;其次,当检测到百米标后,结合图像预处理和卷积循环神经网络(CRNN)网络构建百米标数字文本识别模型,提取百米标的数字文本信息,从而实现对轨道施工车辆的定位。经实验验证该方法能够快速准确定位轨道施工车辆的位置信息。

    Abstract:

    Aiming at the demand of autonomous positioning of rail construction vehicles, this paper proposes a method of absolute position extraction of rail vehicles based on the video of 100-metre markers captured by the on-board forward-looking camera. The method first improves the YOLOX-s network and constructs the target detection model of the 100-metre marker to complete the target detection of the 100-metre marker. Then, when the 100-metre marker is detected, it combines image preprocessing with convolutional recurrent neural network (CRNN) network to construct the 100-metre marker digital text recognition model to extract the digital text information of the 100-metre marker, so as to achieve the absolute position location of rail construction vehicles. The method is verified to be able to quickly and accurately extract the absolute position information of rail construction vehicles.

    参考文献
    [1] 曹海燕, 张大维. 基于机器学习算法的交通标志图像智能识别[J]. 微型电脑应用, 2021,37(1):19.CAO Haiyan, ZHANG Dawei. Intelligent recognition of traffic sign images based on machine learning algorithm[J]. Microcomputer Applications, 2021,37(1):19.
    [2] WELZEL A, REISDORF P, WANIELIK G. Improving urban vehicle localization with traffic sign recognition[C]//2015 IEEE 18th International Conference on Intelligent Transportation Systems. [S.l.]:IEEE, 2015: 2728-2732.
    [3] 张善彬. 基于标准路牌的单目视觉车辆自定位[D]. 青岛:山东大学, 2020.ZHANG Shanbin. Monocular vision vehicle self-localisation based on standard road signs [D]. Qiaodao:Shandong University, 2020.
    [4] 郭保青. 基于图像特征的列车自主定位方法研究[D]. 北京:北京交通大学, 2008.GUO Baoqing. Research on autonomous train positioning method based on image features [D]. Beijing:Beijing Jiaotong University, 2008.
    [5] 曹蜜, 胡凌燕, 熊彭文, 等. 基于PROSAC算法与ORB-SLAM2的RGB-D相机室内视觉定位研究[J]. 传感技术学报, 2019,32(11):1706.CAO Mi, HU Lingyan, XIONG Pengwen, et al. Research on indoor visual localisation of RGB-D camera based on PROSAC algorithm and ORB-SLAM2[J]. Journal of Sensing Technology, 2019,32(11):1706.
    [6] 谢家浩, 刘延飞, 姚二亮. 基于视觉SLAM的拾取目标定位方法研究[J]. 电子设计工程, 2019,27(23):189.XIE Jiahao, LIU Yanfei, YAO Erliang. Research on pickup target localisation method based on visual SLAM[J]. Electronic Design Engineering, 2019,27(23):189.
    [7] POLLEFEYS M, GOOL L V, VERGAUWEN M, et al. Visual modeling with a hand-held camera[J]. International Journal of Computer Vision, 2004,59(3):207.
    [8] HAN G, LI T, LI Q, et al. Improved Algorithm for insulator and its defect detection based on YOLOX[J]. Sensors, 2022,22(16):6186.
    [9] HU J, QIAO P, LV H, et al. High speed railway fastener defect detection by using improved YoLoX-Nano model[J]. Sensors, 2022,22(21):8399.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

沈拓,谢远翔,盛峰,谢兰欣,张颖,安雪晖,曾小清.基于视频的轨道车辆自主定位方法研究[J].同济大学学报(自然科学版),2024,52(2):174~183

复制
分享
文章指标
  • 点击次数:146
  • 下载次数: 435
  • HTML阅读次数: 1066
  • 引用次数: 0
历史
  • 收稿日期:2023-10-24
  • 在线发布日期: 2024-02-27
文章二维码