机器视觉下的钢轨廓形提取与磨耗测量

doi:10.13474/j.cnki.11-2246.2023.0377

测绘通报 ›› 2023, Vol. 0 ›› Issue (12): 159-163,177.doi: 10.13474/j.cnki.11-2246.2023.0377

• 技术交流 • 上一篇

机器视觉下的钢轨廓形提取与磨耗测量

赵静

中铁建(天津)轨道交通投资发展有限公司, 天津 300000

收稿日期:2023-08-29 发布日期:2024-01-08
作者简介:赵静(1984-),女,高级工程师,主要从事轨道交通勘察设计研究及工程技术管理方面的工作。E-mail:124588205@qq.com
基金资助:
天津市交通运输科技发展计划(2022-40)

Extracting rail profile and measuring wear based on machine vision

ZHAO Jing

CRCC(Tianjin)Rail-transit Investment Development Co., Ltd., Tianjin 300000, China

Received:2023-08-29 Published:2024-01-08

摘要/Abstract

摘要： 随着中国高速铁路的迅速发展,传统的接触式钢轨磨耗检测方法测量效率较低且易受钢轨变形与表面伤损的影响,已无法满足钢轨维修养护的需求。为了快速精确测量钢轨廓形及钢轨磨耗,本文提出了一种基于机器视觉的轮廓提取方法,搭建单目机器视觉钢轨廓形提取系统,通过自由平面靶标定位,采用基于结构光颜色和Steger算法的粗精二级钢轨廓形提取方法,提出基于粒子群优化的双圆拟合钢轨廓形匹配算法,实现测量廓形与标准廓形对齐,并得出磨耗值。试验结果表明,该系统检测精度达0.128 mm,同时具备较高的测量效率。

关键词: 高速铁路, 轨道轮廓提取, 线结构光, 光平面标定, 图像处理

Abstract: With the rapid development of China's high-speed railways, traditional contact-based rail wear detection methods have limitations in measurement efficiency and are easily affected by rail deformations and surface damages, failing to meet the demands of the rail maintenance. To quickly and accurately measure the rail profile and assess rail wear, a contour extraction method based on machine vision is proposed. A monocular machine vision system for rail profile extraction has been established. After positioning with a free planar target, a two-level rail profile extraction method based on structured light color and the Steger algorithm is employed. A double circle fitting rail profile matching algorithm based on particle swarm optimization is introduced to align the measured profile with the standard profile and derive the wear value. Experimental results demonstrate that this system achieves a detection accuracy of 0.128 mm and offers high measurement efficiency.

Key words: high-speed rail, rail contour extraction, linear structured light, optical plane calibration, image processing

中图分类号:

赵静. 机器视觉下的钢轨廓形提取与磨耗测量[J]. 测绘通报, 2023, 0(12): 159-163,177.

ZHAO Jing. Extracting rail profile and measuring wear based on machine vision[J]. Bulletin of Surveying and Mapping, 2023, 0(12): 159-163,177.

参考文献

[1] 李响. 基于结构光的钢轨磨耗测量方法研究[D]. 北京: 北京交通大学, 2021.
[2] 王鑫伟. 基于2D激光位移传感器的钢轨磨耗测量方法及应用研究[D]. 长沙: 湖南大学, 2021.
[3] SILVA RAMOS G,ROLF KÜLITZ H,BRUNO TAFFNER M. Prototype of a rail wear measuring system using digital image processing[J]. IEEE Latin America Transactions,2019,17(4): 582-589.
[4] 陈鹏,陈茁,刘秀波,等. 重载铁路曲线区段钢轨侧面磨耗仿真分析[J]. 铁道建筑,2023,63(6): 27-32.
[5] 朱冰冰. 便携式钢轨测量仪的改进及检验[D]. 成都: 西南交通大学,2014.
[6] 陈十进,刘瑾,杨海马,等. 非接触式钢轨三维轮廓参数检测系统研究[J]. 仪表技术与传感器,2019(5): 64-67.
[7] 刘家豪,贺赛先.基于双目便携式三维扫描技术的小工件测量[J].科学技术与工程,2016,16(7):31-41.
[8] DENG Fang,ZHANG Lele,GAO Feng,et al.Long-range binocular vision target geolocation using handheld electronic devices in outdoor environment[J].IEEE Transactions on Image Processing,2020,29:5531-5541.
[9] 罗松. 基于双目立体视觉的被动测距与三维定位[D]. 武汉: 华中科技大学,2015.
[10] YANG Jiachen,XU Ru,DING Zhiyong,et al. 3D character recognition using binocular camera for medical assist[J]. Neurocomputing,2017,220: 17-22.
[11] ZHOU Hongming,HONG T,ZHANG Xianglei,et al. A mathematical model for calculating the theoretical point cloud of gear surface based on line structured light[C]//Proceedings of 2022 International Conference on Optoelectronic Materials and Devices.[S.l.]:SPIE, 2022.
[12] PAN Xinjian,WU Jieying,LI Zhili,et al. Self-calibration for linear structured light 3D measurement system based on quantum genetic algorithm and feature matching[J]. Optik,2021,225: 165749.
[13] YU Haotian,HUANG Yu,ZHENG Dongliang,et al. Three-dimensional shape measurement technique for large-scale objects based on line structured light combined with industrial robot[J]. Optik,2020,202: 163656.
[14] 周小飞,吴文海,于兰英,等.线结构光路面裂缝容积检测技术研究[J].机械设计与制造,2022(12):84-87.
[15] 王昊,王胜春,潘大海,等.车载非接触式钢轨磨耗测量方法研究及应用[J].铁道建筑,2017,57(12):97-101.
[16] 王乐.线结构光钢轨轮廓全断面测量技术研究[D].北京:中国铁道科学研究院,2021.

机器视觉下的钢轨廓形提取与磨耗测量

Extracting rail profile and measuring wear based on machine vision

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	梁策, 黄元库, 刘俊飞, 王万齐, 朱军. 顾及灵敏性利用变形速率判识高铁沉降异常数据[J]. 测绘通报, 2023, 0(9): 150-154.
[2]	贾永红. 数字图像处理混合教学的研究与实践[J]. 测绘通报, 2022, 0(2): 174-176.
[3]	缑永涛, 李文博, 段学锋. 基于无人机的路桥病害检测系统[J]. 测绘通报, 2022, 0(12): 141-146,169.
[4]	程瑞, 高建, 邢强, 孙中昶. 一种优化的Faster R-CNN小目标检测方法[J]. 测绘通报, 2021, 0(9): 21-27.
[5]	唐东跃, 肖书安, 周兴华, 朱水鹏. 三维激光扫描技术在高铁隧道平整度检测中的应用[J]. 测绘通报, 2021, 0(9): 160-164.
[6]	李军, 朱国琦, 樊晓东, 杨维, 黄震. 地铁隧道结构机器视觉检测系统及应用分析[J]. 测绘通报, 2020, 0(9): 27-32,37.
[7]	李航, 马焱, 张翔. 一种网络地图风格化滤镜与中间件技术[J]. 测绘通报, 2020, 0(11): 85-89.
[8]	严成, 何宁, 庞维庆, 邓德迎. 基于机器视觉的水域远程监测应用系统方案设计[J]. 测绘通报, 2019, 0(8): 149-153.
[9]	贾永红, 付仲良, 孙和利. 中国大学MOOC平台数字图像处理在线开放课程的建设与应用[J]. 测绘通报, 2018, 0(12): 144-147.
[10]	潘正风. 高速铁路轨道平面控制网(CPⅢ)测量原理的探讨[J]. 测绘通报, 2016, 0(8): 44-46.
[11]	张嵘. 基于Matlab平台的遥感图像变化检测算法改进策略[J]. 测绘通报, 2016, 0(7): 84-89.
[12]	赵尘衍, 徐亚明, 张涛. 单目视觉位移在线监测系统的设计与实现[J]. 测绘通报, 2016, 0(6): 121-124.
[13]	张吉春, 明祖涛. 一种计算高铁沉降预测常用模型参数的新方法[J]. 测绘通报, 2016, 0(1): 95-98.
[14]	王振华, 胡翔云, 单杰. 众源GPS浮动车数据中城市道路中心线分级提取的栅格化方法[J]. 测绘通报, 2015, 0(8): 22-24,34.
[15]	肖化超周诠张建华. 遥感卫星在轨机场变化检测方法[J]. 测绘通报, 2015, 0(1): 22-25.