• ISSN 0258-2724
  • CN 51-1277/U
  • EI Compendex
  • Scopus 收录
  • 全国中文核心期刊
  • 中国科技论文统计源期刊
  • 中国科学引文数据库来源期刊

知识引导的铁路站场接触网点云导线特征智能提取方法

朱军 张传军 赵剑峰 王学柱 付林 黄智勇 郭鹏飞

陈维荣, 胡斌彬, 李奇, 燕雨, 孟翔. 基于动态规划的混合动力有轨电车能量管理方法[J]. 西南交通大学学报, 2020, 55(5): 903-911. doi: 10.3969/j.issn.0258-2724.20180470
引用本文: 朱军, 张传军, 赵剑峰, 王学柱, 付林, 黄智勇, 郭鹏飞. 知识引导的铁路站场接触网点云导线特征智能提取方法[J]. 西南交通大学学报. doi: 10.3969/j.issn.0258-2724.20230435
CHEN Weirong, HU Binbin, LI Qi, YAN Yu, MENG Xiang. Energy Management Method for Hybrid Electric Tram Based on Dynamic Programming Algorithm[J]. Journal of Southwest Jiaotong University, 2020, 55(5): 903-911. doi: 10.3969/j.issn.0258-2724.20180470
Citation: ZHU Jun, ZHANG Chuanjun, ZHAO Jianfeng, WANG Xuezhu, FU Lin, HUANG Zhiyong, GUO Pengfei. Intelligent Extraction Method of Railway Station Overhead Catenary Wire Features from Point Cloud Guided by Knowledge[J]. Journal of Southwest Jiaotong University. doi: 10.3969/j.issn.0258-2724.20230435

知识引导的铁路站场接触网点云导线特征智能提取方法

doi: 10.3969/j.issn.0258-2724.20230435
基金项目: 国家自然科学基金项目(42271424)
详细信息
    作者简介:

    朱军(1976—),男,教授,博士,研究方向为三维地理信息系统与虚拟地理环境,E-mail:zhujun@swjtu.edu.cn

  • 中图分类号: P232

Intelligent Extraction Method of Railway Station Overhead Catenary Wire Features from Point Cloud Guided by Knowledge

  • 摘要:

    为解决铁路站场接触网点云噪声分布不规律及语义分割难度大的问题,提出一种智能提取方法,以增强接触网异常检测能力. 首先,对站场接触网场景数据进行深入分析,构建导线及钢轨顶面点云提取的知识框架;其次,考虑站场接触网点云空间特征,设计站场关键要素点云的分割与融合滤波方法;然后,建立站场接触网强空间语义约束规则,提出知识引导的导线特征智能精细提取方法;基于此,采用WHU-TLS等站场点云数据集,搭建实验平台并开展实验分析,实验结果表明:在部分点云缺失以及噪声干扰等复杂环境下,本文方法易于操作且自动化程度高,相比传统导线特征提取方法耗时最少,100 m范围内站场接触网导线特征提取的平均精度达到±5 mm,能够有效支撑铁路站场接触网几何特征的智能检测.

     

  • 图 1  总体研究框架

    Figure 1.  Overview of the research framework

    图 2  预处理算法结构框架

    Figure 2.  Preprocessing algorithm framework

    图 3  接触网导线参数智能提取

    Figure 3.  Intelligent extraction of catenary wire parameters

    图 4  导线点云自适应邻域点选择

    Figure 4.  Adaptive neighborhood point selection of wire point cloud

    图 5  接触网导线精细提取方法

    Figure 5.  Method for Precise Extraction of Catenary Wire

    图 6  P60钢轨点云模型

    Figure 6.  Point Cloud Model of P60 Steel Rail

    图 7  站场接触网原始点云

    Figure 7.  Original point cloud of catenary in railway station

    图 8  站场点云分类滤波抽稀结果

    Figure 8.  Results of point cloud classification, filtering, and thinning

    图 9  接触网导线结点局部图

    Figure 9.  Local diagram of catenary wire node

    图 10  接触网导线与钢轨顶面分割结果

    Figure 10.  Catenary wire and rail top surface segmentation results

    图 11  导线几何特征超限预警系统

    Figure 11.  Parameter out-of-range warning system

    表  1  软硬件配置

    Table  1.   Hardware and software configuration

    环境配置 详细信息
    硬件CPU12th Gen Intel Core i7-12700H
    内存16 GB
    显卡NVIDIA GeForce RTX 3060
    软件系统Windows11
    软件PCL1.12.1、VS2019
    下载: 导出CSV

    表  2  接触网导线点云分割算法对比

    Table  2.   Accuracy of contact wire point cloud extraction

    方法处理范围耗时鲁棒性精确度
    本文方法长距离最少一般最好
    RANSAC短距离较多较强一般
    3D Hough短距离最多较强最差
    下载: 导出CSV

    表  3  接触网导线特征提取结果

    Table  3.   Exaction results of contact wire features mm

    组号 导高 实测
    导高
    导高
    差值
    拉出值 实测拉出值 拉出值差值
    1 5306 5311 −5 193 199 −6
    2 5300 5297 3 197 205 −8
    3 5304 5310 −6 214 212 2
    4 5304 5305 −1 220 218 2
    5 5299 5294 5 223 223 0
    6 5303 5297 6 230 231 −1
    7 6449 6447 2 200 202 −2
    8 6447 6450 −3 211 218 −7
    9 6458 6464 −6 224 225 −1
    10 6450 6456 −6 238 243 −5
    下载: 导出CSV
  • [1] 中华人民共和国国务院. “十四五” 现代综合交通运输体系发展规划[EB/OL]. (2021-12-09)[2023-08-01]. https://xxgk.mot.gov.cn/2020/jigou/zhghs/202201/t20220119_3637245.html.
    [2] 于万聚. 高速电气化铁路接触网[M]. 成都:西南交通大学出版社,2003:323-344.
    [3] 孔龙飞,韩通新. 基于激光雷达的接触网动态几何参数安全监测研究[J]. 铁道机车车辆,2019,39(4): 86-89,123. doi: 10.3969/j.issn.1008-7842.2019.04.19

    KONG Longfei, HAN Tongxin. Research on safety monitoring of dynamic geometric parameters of catenary based on laser scanning radar[J]. Railway Locomotive & Car, 2019, 39(4): 86-89,123. doi: 10.3969/j.issn.1008-7842.2019.04.19
    [4] 刘继冬,梁茹楠,陈交,等. 接触网承力索集中荷载测量方法[J]. 西南交通大学学报,2024,59(3): 510-518. doi: 10.3969/j.issn.0258-2724.20211092

    LIU Jidong, LIANG Runan, CHEN Jiao, et al. Measurement method for concentrated load on catenary messenger wires[J]. Journal of Southwest Jiaotong University, 2024, 59(3): 510-518. doi: 10.3969/j.issn.0258-2724.20211092
    [5] 周宁,支兴帅,张静,等. 电气化铁路弓网系统摩擦磨损性能研究进展[J]. 西南交通大学学报,2024,59(5): 990-1005. doi: 10.3969/j.issn.0258-2724.20220053

    ZHOU Ning, ZHI Xingshuai, ZHANG Jing, et al. Friction and wear performance of pantograph-catenary system in electrified railways: state of the art[J]. Journal of Southwest Jiaotong University, 2024, 59(5): 990-1005. doi: 10.3969/j.issn.0258-2724.20220053
    [6] DEHBI Y, HENN A, GRÖGER G, et al. Robust and fast reconstruction of complex roofs with active sampling from 3D point clouds[J]. Transactions in GIS, 2021, 25(1): 112-133. doi: 10.1111/tgis.12659
    [7] TON B, AHMED F, LINSSEN J. Semantic segmentation of terrestrial laser scans of railway catenary Arches: a use case perspective[J]. Sensors, 2022, 23(1): 222.1-222.14.
    [8] HAN F, LIANG T, REN J P, et al. Automated extraction of rail point clouds by multi-scale dimensional features from MLS data[J]. IEEE Access, 2023, 11: 32427-32436. doi: 10.1109/ACCESS.2023.3262732
    [9] 梁涛,韩峰,陈国栋. 基于连续点云数据的既有铁路轨面信息快速提取算法设计[J]. 铁道科学与工程学报,2021,18(10): 2544-2551.

    LIANG Tao, HAN Feng, CHEN Guodong. Algorithm design for fast extraction of rail-surface information for existing railway based on continuous point cloud data[J]. Journal of Railway Science and Engineering, 2021, 18(10): 2544-2551.
    [10] SÁNCHEZ-RODRÍGUEZ A, SOILÁN M, CABALEIRO M, et al. Automated inspection of railway tunnels' power line using LiDAR point clouds[J]. Remote Sensing, 2019, 11(21): 2567.1-2567.13.
    [11] 周靖松,韩志伟,杨长江. 基于三维点云的接触网几何参数检测方法[J]. 仪器仪表学报,2018,39(4): 239-246.

    ZHOU Jingsong, HAN Zhiwei, YANG Changjiang. Catenary geometric parameters detection method based on 3D point cloud[J]. Chinese Journal of Scientific Instrument, 2018, 39(4): 239-246.
    [12] 麻卫峰,王成,王金亮,等. 激光点云输电线精细提取的残差聚类法[J]. 测绘学报,2020,49(7): 883-892.

    MA Weifeng, WANG Cheng, WANG Jinliang, et al. Extraction of power lines from laser point cloud based on residual clustering method[J]. Acta Geodaetica et Cartographica Sinica, 2020, 49(7): 883-892.
    [13] MA T, LONG X, FENG L, et al. Visible neighborhood graph of point clouds[J]. Graphical Models, 2012, 74(4): 184-196. doi: 10.1016/j.gmod.2012.04.007
    [14] TIAN F J, JIANG Z D, JIANG G Y. DNet: dynamic neighborhood feature learning in point cloud[J]. Sensors, 2021, 21(7): 2327.1-2327.20.
    [15] 赵明富,曹利波,宋涛,等. 三维点云配准中FPFH邻域半径自主选取算法[J]. 激光与光电子学进展,2021,58(6): 123-131.

    ZHAO Mingfu, CAO Libo, SONG Tao, et al. Independent method for selecting radius of FPFH neighborhood in 3D point cloud registration[J]. Laser & Optoelectronics Progress, 2021, 58(6): 123-131.
    [16] 魏双全,房华乐,林祥国. 先验知识引导的车载激光扫描点云道路信息提取[J]. 测绘科学,2014,39(10): 81-84.

    WEI Shuangquan, FANG Huale, LIN Xiangguo. Road information extraction from mobile laser scanning point cloud based on priori knowledge[J]. Science of Surveying and Mapping, 2014, 39(10): 81-84.
    [17] 方一鹏,宋占峰,李军. 基于TLS数据的站场线路点云提取算法[J]. 铁道科学与工程学报,2024,21(2): 545-554.

    FANG Yipeng, SONG Zhanfeng, LI Jun. Point cloud extraction algorithm based on TLS data in railway stations[J]. Journal of Railway Science and Engineering, 2024, 21(2): 545-554.
    [18] 朱军,陈逸东,张昀昊,等. 网络环境下全景图和点云数据快速融合可视化方法[J]. 西南交通大学学报,2022,57(1): 18-27. doi: 10.3969/j.issn.0258-2724.20200360

    ZHU Jun, CHEN Yidong, ZHANG Yunhao, et al. Visualization method for fast fusion of panorama and point cloud data in network environment[J]. Journal of Southwest Jiaotong University, 2022, 57(1): 18-27. doi: 10.3969/j.issn.0258-2724.20200360
    [19] CHEN X, CHEN Z, LIU G X, et al. Railway overhead contact system point cloud classification[J]. Sensors, 2021, 21(15): 4961.1-4691.22.
    [20] XU L, ZHENG S Y, NA J M, et al. A vehicle-borne mobile mapping system based framework for semantic segmentation and modeling on overhead catenary system using deep learning[J]. Remote Sensing, 2021, 13(23): 4939.1-4939.22.
    [21] 郭保青,余祖俊,张楠,等. 铁路场景三维点云分割与分类识别算法[J]. 仪器仪表学报,2017,38(9): 2103-2111. doi: 10.3969/j.issn.0254-3087.2017.09.002

    GUO Baoqing, YU Zujun, ZHANG Nan, et al. 3D point cloud segmentation, classification and recognition algorithm of railway scene[J]. Chinese Journal of Scientific Instrument, 2017, 38(9): 2103-2111. doi: 10.3969/j.issn.0254-3087.2017.09.002
    [22] 霍佳欣,杨家志. 统计学滤波和引导滤波相结合的点云数据降噪[J]. 计算机应用与软件,2023,40(5): 248-252,287. doi: 10.3969/j.issn.1000-386x.2023.05.037

    HUO Jiaxin, YANG Jiazhi. Point cloud data denoising method combining statistical filtering and guided filtering[J]. Computer Applications and Software, 2023, 40(5): 248-252,287. doi: 10.3969/j.issn.1000-386x.2023.05.037
    [23] 惠振阳,李娜,程朋根,等. 基于连通性标记优化的地基LiDAR点云单木分割方法[J]. 中国激光,2023,50(6): 155-163.

    XI/HUI) Zhenyang, LI Na, CHENG Penggen, et al. Single tree segmentation method for terrestrial LiDAR point cloud based on connectivity marker optimization[J]. Chinese Journal of Lasers, 2023, 50(6): 155-163.
    [24] HUI Z, LI N, XIA Y, et al. Individual tree extraction from uav LIDAR point clouds based on self-adaptive mean shift segmentation[J]. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, 2021, 51: 25-30.
    [25] 国家铁路局. 铁路线路设计规范:TB 10098—2017[S]. 北京:中国铁道出版社,2017
    [26] 国家铁路局. 铁路车站及枢纽设计规范:TB 10099—2017[S]. 北京:中国铁道出版社,2017.
    [27] 中国铁路总公司. 高速铁路接触网运行维修规则:TG/GD 124—2015[S]. 北京:中国铁道出版社,2015.
    [28] DONG Z, LIANG F X, YANG B S, et al. Registration of large-scale terrestrial laser scanner point clouds: a review and benchmark[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 163: 327-342. doi: 10.1016/j.isprsjprs.2020.03.013
  • 加载中
图(11) / 表(3)
计量
  • 文章访问数:  51
  • HTML全文浏览量:  23
  • PDF下载量:  7
  • 被引次数: 0
出版历程
  • 收稿日期:  2023-08-29
  • 修回日期:  2024-03-26
  • 网络出版日期:  2025-01-23

目录

    /

    返回文章
    返回