计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (3): 214-224.doi: 10.11896/jsjkx.250400009

• 计算机图形学 & 多媒体 • 上一篇    下一篇

计算机视觉在轨道交通中的应用

赵斌贝, 朱力, 赵红礼, 李雨彤   

  1. 北京交通大学自动化与智能学院 北京 100044
  • 收稿日期:2025-04-01 修回日期:2025-07-17 发布日期:2026-03-12
  • 通讯作者: 朱力(lizhu@bjtu.edu.cn)
  • 作者简介:(22211320@bjtu.edu.cn)
  • 基金资助:
    国家重点研发计划(2024YFB3108600)

Computer Vision Applications in Rail Transit Systems

ZHAO Binbei, ZHU Li, ZHAO Hongli, LI Yutong   

  1. School of Automation and Intelligence, Beijing Jiaotong University, Beijing 100044, China
  • Received:2025-04-01 Revised:2025-07-17 Online:2026-03-12
  • About author:ZHAO Binbei,born in 2004,undergra-duate.Her main research interests include computer vision and traffic control.
    ZHU Li,born in 1984,Ph.D,professor,Ph.D supervisor.His main research interests include artificial intelligence,intelligent control and optimization of transportation,and perception and big data of transportation systems.
  • Supported by:
    National Key Research and Development Program of China(2024YFB3108600).

PDF (PC)

122

摘要： 轨道交通系统作为交通网络的骨干,因具有高效、便捷的特点,在现代社会中扮演着至关重要的角色。随着技术的持续进步,计算机视觉技术已成为推动轨道交通系统向更高效和更可靠发展的关键因素。对此,深入探讨了计算机视觉技术在轨道交通领域的研究现状,评估了该技术对提升运输效率和安全性的重要贡献,并分析了在实际应用中遇到的挑战以及可能的改进方向。从车站安全检测、轨道安全检测和车体状态检测这3个应用方向,分析了计算机视觉技术的应用内容以及当前研究的发展方向。最后,对未来发展趋势进行了展望,预测了计算机视觉技术将如何进一步推动轨道交通系统的自动化、智能化,以及在保障数据安全的前提下,为轨道交通领域带来更多创新和突破。

关键词: 计算机视觉, 轨道交通, 特征提取, 目标检测

Abstract: As the backbone of transportation networks,rail transit systems play a pivotal role in modern society due to their high efficiency and operational reliability.With continuous technological advancements,computer vision technologies have emerged as a critical driver for enhancing rail transit systems toward greater efficiency and dependability.This paper comprehensively examines the current research landscape of computer vision applications in rail transit,evaluates their significant contributions to improving transportation efficiency and safety,and analyzes both the challenges encountered in practical implementations and potential improvement strategies.Through systematic analysis of three primary application domains－station security surveillance,track condition monitoring,and rolling stock status assessment－the study elucidates the implementation frameworks of computer vision technologies while identifying current research trajectories.Finally,the paper provides a forward-looking perspective on development trends,predicting how computer vision will further propel automation and intelligentization in rail transit systems.It also anticipates innovative breakthroughs in this field while ensuring data security compliance,ultimately fostering safer and more sustainable urban transportation ecosystems.

Key words: Computer vision, Rail transit, Feature extraction, Object detection

中图分类号: 

  • TP181
[1]QI X Y.Application of Computer Vision Technology in the Monitoring of Rail Transit Drivers[J].Technology and Information,2025(6):168-170.
[2]HUANG K N.Promotion of Computer Vision Technology onIntelligent Transportation System Development[J].Journal of Huanghe S & T College,2022,24(8):59-63.
[3]CHEN Q L,MA Y T.Exploring & Discussing on the Applications and Key Technologies of Computer Technology in Gra-phics and Image Processing[J].Office Informatization,2024,29(14):4-6.
[4]WEI Y Y,MAO T Y,LI B A,et al.Visual and large multimodal models promote image restoration and enhancement:research progres[J].Journal of Image and Graphics,2025,30(5):1197-1219.
[5]JIANG D D.Edge Detection in Conveyor Belt Images Using an Enhanced Sobel Operator[J].Mining Equipment,2024(5):10-12.
[6]Review of One-Stage Universal Object Detection Algorithms in Deep Learning[J].Journal of Frontiers of Computer Science and Technology,2025,19(5):1115-1140.
[7]GUO H S.Object detection:From traditional methods to deep learning[J].Emerging Science and Technology,2024,3(2):128-145.
[8]ZHU X J,FAN C H,WANG Y H,et al.Design of a teaching platform for NeRF 3D scene reconstruction system based on robotic arm[J].China Educational Technologyand Equipment,2025(8):31-33,42.
[9]TAN F G,LIAO Q M,ZHAI C.Research on Lightweight Object Detection of YOLOv5 Based on Vehicle Vision in Urban Rail Transit[J].Journal of Guangdong Communication Polytechnic,2024,23(1):45-48,80.
[10]ZHENG S Z.Taxonomy and Enhancement Prospects of Net-work Models in Object Classification and Detection Tasks[J].Information China,2024(4):243-246.
[11]XU J G,HAN J M,LIU Y,et al.Inspection of State of Registration Devices Based on Machine Vision and 3D Point Cloud[J].Journal of Railway Engineering Society,2024,41(5):73-78,93.
[12]YANG Q X,REN R L,MA Q M,et al.Based on 3D laser scanning and BIM intergrated technology 3D modeling method of underground buildings in urban rail transit[J].Bulletin of Surveying and Mapping,2024(4):119-123.
[13]LIU M M,LU J F,LIU H,et al.Image Description Generation Method by Panoptic Segmentation and Multi-Visual-Feature Fusion[J].Computer Engineering,2024,50(11):308-317.
[14]MENG Q Q,LI D F,XIAO W T.Canny Edge Detection of Complex Image Based on Double Sparse Decomposition[J].Computer & Digital Engineering,2024,52(4):1164-1168,234.
[15]GAO R,XIONG Y P,WEI C F.Multi-Task Perception Algor-ithm for Rail Transit Scenarios Based on Triplet Attention[J].Control and Information Technology,2024(5):47-56.
[16]YANG S R,YANG H C,SHEN F R,et al.Image Data Augmentation for Deep Learning:A Survey[J].Journal of Software,2025,36(3):1390-1412.
[17]ZHANG J L,YANG J,LIU X B,et al.Computer Vision-based Fire Detection and Localization Inside Urban Rail Transit Stations[J].Journal of Transportation Systems Engineering and Information Technology,2024,24(3):53-63.
[18]TIAN J Q,QIN G X,ZHANG W.Fire-and-smoke detection algorithm based on convolutional attention and feature fusion[J/OL].Journal of Beijing University of Aeronautics and Astronautics,2024,doi:10.13700/j.bh.1001-5965.
[19]ZHANG H X,LIU Y R,LIU Y,et al.A multitask learning model for the prediction of short-term subway passenger flow[J].Shandong Science,2024,37(1):95-106.
[20]SHI X,LI H,LI X Y,et al.Research on a New Target Detection Algorithm for the Large Passenger Flow Environment of Metro[J].Digital Communication World,2023,(1):52-54,65.
[21]ZHANG J L,CHEN Y,YANG L X,et al.Computer vision-based detection and prediction model for passenger flows inside urban rail transit stations[J].Journal of Railway Science and Engineering,2023,20(10):3696-3704.
[22]ZHANG H W.Automatic Surface Defect Detection Method of Railway Ballastless Track Based on Visual Feature[J].Automation Application,2023,64(15):144-146.
[23]TAO P,FANG Y,WANG X,et al.Multi-task track defect detection method based on improved SAM model[J].Journal of Nanjing University(Natural Science),2024,60(5):776-784.
[24]GAN L Q,PENG C Y,QIU C R,et al.Metro ballast anomaly detection method based on normalizing flow[J].Modern Electronics Technique,2024,47(9):119-123.
[25]YANG H M.State Detection Method of Rail Transit Catenary Rotary Double Ears Based on Machine Vision[J].Urban Mass Transit,2023,26(9):238-243.
[26]YU Q B,NI G Z,WANG Z R.Online Safety Monitoring System for OCS in Urban Rail Transit[J].China Railway,2024(3):50-56.
[27]WANG K P,LI W.Intelligent Anomaly Detection Method for Pantograph Contact Strip Abnormalities Based on Deep Lear-ning[J].China Equipment Engineering,2023(9):192-194.
[28]LI Y P,LI G,LUO Y J.Edge Detection Method of Pantograph Carbon Slide Plate Based on Wavelet and Curvelet Transform[J].Machinery,2024,51(7):37-44.
[29]ZENG G,HUANG Y L,TONG J Q,et al.Research and Implementation of a Machine Vision Based Wear Detection System for Pantograph Skateboards[J].Automation Application,2024,65(12):193-196.
[30]YE T,QIN W Y,ZHANG X.Experimental platform design of automatic obstacle detection system based on millimeter wave radar and computer vision[J].Experimental Technology and Management,2022,39(1):136-141.
[31]LONG L B,ZHAO H,YANG C,et al.Machine-vision based method and apparatus for in-situmeasurement of railway turnout parameters[J].Journal of Electronic Measurement and Instrumentation,2023,37(4):80-89.
[32]WU X C,YIN L,WAN M H.A Machine Vision-Based Rapid Detection Method for Switch Blade Gaps[J].Science and Technology & Innovation,2024(8):77-78,82.
[33]ZHAO Z Y,KANG J H,LIANG J,et al.All-weather intelligent detection system for railway intrusion obstacles based on LGF-Net[J].Chinese Journal of Scientific Instrument,2023,44(9):287-301.
[34]ZHAO Z Y,KANG J H,WU B,et al.Research on the high robust multi-scale few-shot railway intrusion obstacles detection method based on FRL-Net[J].Chinese Journal of Scientific Instrument,2024,45(1):239-249.
[35]DU K H,XU G Y,BAI T B.Vanilla-YOLOv8 railway foreign object intrusion detection method based on feature redundancyreduction[J].Journal of Beijing Jiaotong University,2024,48(5):49-58.
[36]SONG H J.Necessity Analysis and Mitigation Strategies forForeign Object Intrusion Detection in Railway Tracks[J].Science & Technology Vision,2022(5):136-138.
[37]SHI H.Image Contrast Technology-Based Method for Defect Detection in Metro Car Bodies[J].China Plant Engineering,2023(11):194-196.
[38]LI S T,XUE Y D,CHI S C,et al.Intelligent lost and loose detection of track fastener components based on 3D camera[J].Journal of Railway Science and Engineering,2024,21(1):386-395.
[39]LIU L X Y,PENG L T,LI C,et al.Anomaly Detection of Train Components Based on 3D Point Cloud[J].Artificial Intelligence and Robotics Research,2023,12(4):267-280.
[40]WANG Z J,GU F,ZENG Z.Research on the Detection Method of Loose Roof Bolts of Low-quality Rail Vehicles[J].Machine Design & Research,2024,40(2):220-224.
[41]YANG W,YANG K,QIU C R,et al.Anomaly Detection Algorithm of Ballastless Track Bed Based on Image Inpainting[J].Laser & Optoelectronics Progress,2024,61(12):410-421.
[42]HUANG T,ZHANG J X,CAI Z K,et al.Research on UrbanRail Transit Train Positioning and Speed Measurement System Based on Machine Vision Technology[J].Urban Mass Transit,2022,25(7):8-12.
[43]SHEN J W,LU Y M,CHEN X Y,et al.Review of Research on Human Behavior Detection Methods Based on Deep Learning[J].Computer and Modernization,2023(9):1-9.
[44]ZHENG Z X,FAN K,DENG J X.Application Research of Rail Transit Operating Environment Perception Technology Based on Improved Mask-R-CNN Network[J].Railway Transport and Economy,2024,46(1):184-191,198.
[45]HE L,FENG Y Y.Cloud Computing and Big Data-Driven Optimization Strategies for Urban Rail Transit Operations Management Systems[J].High Speed Rail Courier,2024(13):49-51.
[46]LIU X.Full Throttle Computing:AI Integration Docks at the Station of Technological Convergence[J].Digital Economy,2024(5):38-41.
[47]WANG S Y.Multi-Sensor Fusion-Based Foreign Object Detection System for Railway Tracks[J].Manufacture & Upgrading Today,2023(12):87-90.
[48]YAN Z Y,WANG J X.Research on multimodal intelligent ticketing service mode of Beijing-Zhangjiakou high-speed railway[J].Railway Computer Application,2021,30(7):14-20.
[49]CHENG Y,LIU J C,ZHANG C L,et al.Review of the Applied Research on Multimodal Deep Learning in Rail Top Surface Defect Detection[J].China Railway Science,2025,46(1):70-86.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发