光流法在地铁车辆测速中的应用研究

吕红强; 黄涛; 聂兴家; 陈柯宇; 蔡正凯; 单奇

doi:10.13890/j.issn.1000-128X.2022.02.018

您当前的位置：

首页 >

文章列表页 >

光流法在地铁车辆测速中的应用研究

关键技术与材料 | 更新时间：2024-08-02

- 光流法在地铁车辆测速中的应用研究
- Application of optical flow method in metro train speed measurement
- 机车电传动 2022年第2期页码：129-134
- 作者机构：
  
  1.中车南京浦镇车辆有限公司，江苏南京 210031
  2.西南交通大学机械工程学院，四川成都;610031
- 作者简介：
  
  单　奇（1965—），男，博士，副教授，研究方向为测控网络技术与系统集成；E-mail: 759173178@qq.com
- 基金信息：
  
  国家自然科学基金项目(51605393);国家重大技术装备攻关工程项目（系列化中国标准地铁列车研制及试验）
- DOI：10.13890/j.issn.1000-128X.2022.02.018
  中图分类号： U231
- 纸质出版日期：2022-03-10，
  
  收稿日期：2021-09-08，
  
  修回日期：2022-03-01，
- 稿件说明：
扫描看全文
吕红强, 黄涛, 聂兴家, 等. 光流法在地铁车辆测速中的应用研究[J]. 机车电传动, 2022,(2):129-134.

LYU Hongqiang, HUANG Tao, NIE Xingjia, et al. Application of optical flow method in metro train speed measurement[J]. Electric drive for locomotives, 2022,(2):129-134.
吕红强, 黄涛, 聂兴家, 等. 光流法在地铁车辆测速中的应用研究[J]. 机车电传动, 2022,(2):129-134. DOI： 10.13890/j.issn.1000-128X.2022.02.018.

LYU Hongqiang, HUANG Tao, NIE Xingjia, et al. Application of optical flow method in metro train speed measurement[J]. Electric drive for locomotives, 2022,(2):129-134. DOI： 10.13890/j.issn.1000-128X.2022.02.018.

摘要

地铁车辆速度是列控系统的一项重要参数，传统的地铁车辆测速方法存在一定的缺陷。文章利用图像处理中的光流法研究地铁车辆测速新方法，提出了满足地铁车辆测速实时性和精度要求的快速光流计算方法。引入图像金字塔，通过由粗到精、逐层细化的步骤求解大位移运动光流，解决了LK光流法无法计算大位移运动的缺陷；提出了将GPU用于光流计算，实现图像特征点检测计算并行化，显著提升光流计算速度；设计了线路仿真软件进行测速仿真试验。结果表明，基于图像金字塔的光流改进算法提高了大位移情况下光流估计精度，基于GPU的光流并行计算有效提高了光流计算速度，满足地铁车辆测速系统的实时性要求。通过搭建支撑平台，并进行实际线路试验，进一步验证了光流测速方法的可行性。

Abstract

Subway speed is an important parameter of train control system. The traditional subway speed measurement methods have some defects. In this paper

a new method of subway speed measurement by using the optical flow method in image processing was explored

and a fast optical flow calculation method to meet the requirements of real-time and accuracy of subway speed measurement was put forward. The image pyramid was introduced to solve the optical flow of large displacement motion through the method of coarse to fine and layer by layer refinement

which solved the defect that LK optical flow method could not calculate large displacement motion; GPU was used in optical flow calculation to realize the parallelization of image feature point detection and calculation

which significantly improved the speed of optical flow calculation; The line simulation software was designed for speed measurement simulation experiment. The results show that the improved optical flow algorithm based on image pyramid can improve the accuracy of optical flow estimation under large displacement

and the optical flow parallel calculation based on GPU can effectively improve the optical flow calculation speed and meet the real-time requirements of metro speed measurement system. The feasibility of the speed measurement method in this paper is further verified by building the machine support platform and carrying out the actual line experiment.

关键词

地铁测速光流法GPU加速实时性仿真

Keywords

metro trainspeed measurementoptical flow methodGPU accelerationreal timesimulation

references

陆东福. 交通强国　铁路先行　为促进经济社会持续健康发展做出更大贡献——在中国铁路总公司工作会议上的报告(摘要)[J]. 铁路计算机应用, 2018, 27(1): 1-3.

LU Dongfu. Transportation power, railway first behavior and make greater contribution to the sustainable and healthy development of economy and society-report at the working meeting of China railway corporation (Abstract)[J]. Railway Computer Application, 2018, 27(1): 1-3.

蔡伯根, 王剑, 刘江, 等. 列车运行控制系统测速定位技术[M]. 北京: 中国铁道出版社, 2018.

CAI Bogen, WANG Jian, LIU Jiang, et al. Speed measurement and positioning technology of train operation control system[M]. Beijing: China Railway Publishing House, 2018.

LAUZE F, KORNPROBST P, MEMIN E. A coarse to fine multiscale approach for linear least squares optical flow estimation[C]// Proceedings of the British Machine Vision Conference. [S.l.]: BMVA Press, 2004. DOI: 10.5244/C.18.79http://dx.doi.org/10.5244/C.18.79.

KIM Y H, MARTI´NEZ A M, KAK A C. Robust motion estimation under varying illumination[J]. Image and Vision Computing, 2005, 23: 365-375.

BROX T, MALIK J. Large displacement optical flow: descriptor matching in variational motion estimation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(3): 500-513.

卢宗庆. 运动图像分析中的光流计算方法研究[D]. 西安: 西安电子科技大学, 2007.

LU Zongqing. Research on optical flow computation for motion image analysis[D]. Xi'an: Xidian University, 2007.

张永亮, 卢焕章, 高劼, 等. 一种改进的Lucas-Kanade光流估计方法[J]. 海军航空工程学院学报, 2009, 24(4): 443-446.

ZHANG Yongliang, LU Huanzhang, GAO Jie, et al. Improvement of Lucas-Kanade method for optical flow estimation[J]. Journal of Naval Aeronautical and Astronautical University, 2009, 24(4): 443-446.

齐蕴光, 安钢, 张建. 基于饱和度梯度的彩色序列图像光流场计算[J]. 装甲兵工程学院学报, 2012, 26(3): 69-73.

QI Yunguang, AN Gang, ZHANG Jian. Optical flow field computation of color image sequence based on saturation gradient[J]. Journal of Armored Force Engineering Institute, 2012, 26(3): 69-73.

马龙, 王鲁平, 陈小天, 等. 噪声环境下光流场估计方法[J]. 信号处理, 2012, 28(1): 87-91.

MA Long, WANG Luping, CHEN Xiaotian, et al. Determining optical flow field in the presence of noise[J]. Signal Processing, 2012, 28(1): 87-91.

李喆. 一种Lucas-Kanade光流金字塔算法的伪特征点移除方法[D]. 长春: 吉林大学, 2016.

LI Zhe. A method of removing false features of Lucas-Kanade flow pyramidal implementation[D]. Changchun: Jilin University, 2016.

李成美, 白宏阳, 郭宏伟, 等. 一种改进光流法的运动目标检测及跟踪算法[J]. 仪器仪表学报, 2018, 39(5): 249-256.

LI Chengmei, BAI Hongyang, GUO Hongwei, et al. Moving object detection and tracking based on improved optical flow method[J]. Chinese Journal of Scientific Instrument, 2018, 39(5): 249-256.

GIBSON J J. The perception of the visual world[M]. Boston: Houghton Mifflin, 1950.

杨盛伟. 无人机光流测速优化算法研究[D]. 南京: 南京航空航天大学, 2019.

YANG Shengwei. Research on optical flow velocity measurement optimization algorithm for rotor UAV[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2019.

浏览量

下载量

CSCD

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

吊弦故障影响下的接触网锚段区域动态行为研究

基于电机振动的动车组牵引逆变器故障诊断研究

基于潮流转移装置的混合储能接入牵引供电系统控制策略研究

新型160 km/h铁路货运棚车车门疲劳寿命研究

基于改进跟踪微分器的磁浮列车悬浮控制研究