| 22 | 0 | 14 |
| 下载次数 | 被引频次 | 阅读次数 |
轨道交通系统作为城市重要的交通基础设施，其安全性和可靠性直接关系到人民群众的出行安全和国家经济社会的稳定发展。轨道交通轨行区异物入侵将直接给列车安全运行带来威胁，因此，轨道交通轨行区异物的及时发现和准确检测就显得尤为重要。首先，对轨道交通轨行区异物入侵自动检测技术进行综述，分别从基于图像处理、深度学习和多传感器融合三类方法进行阐述。其次，分别介绍了国内外轨道交通轨行区异物入侵检测系统应用现状。最后，阐述了轨道交通轨行区异物自动检测技术仍面临的挑战和未来发展方向，以期为相关研究提供参考和启示。
Abstract：As an important transportation infrastructure in cities,the safety and reliability of the rail transit system are directly related to the travel safety of the people and the stable development of the national economy and society.The intrusion of foreign objects into rail transit track areas poses an immediate threat to the safe operation of trains.Therefore,the timely detection and accurate identification of foreign objects in rail transit track areas are particularly important.This paper first reviews the automatic detection technologies for foreign objects intrusion in rail transit track operation zones,elaborating on three categories of methods:image processing-based,deep learning-based,and multi-sensor fusion-based approaches.Second,it introduces the current application status of foreign objects intrusion detection systems in rail transit track operation zones both domestically and internationally.Finally,it discusses the remaining challenges and future development directions of automatic foreign objects detection technology in rail transit track operation zones,aiming to provide references and insights for related research.
[1]中国城市轨道交通协会.城市轨道交通2023年度统计和分析报告[EB/OL].(2024-03-29)[2024-10-25].https://www.camet.org.cn/xytj/tjxx/14894.shtml.
[2]Zheng Z.X,Wang H,Liu W.M,et.al.Toward real-time congestion measurement of passenger flow on platform screen doors based on surveillance videos analysis[J].Physica A:Statistical Mechanics and its Applications,2023(612):128474.
[3]谭飞刚，廖全蜜，翟聪.城市轨道交通车载视觉YOLOv5轻量化目标检测研究[J].广东交通职业技术学院学报，2024,23(1):45-48,80.
[4]管岭，贾利民，谢征宇.融合注意力机制的轨道入侵异物检测轻量级模型研究[J].铁道学报，2023,45(5):72-81.
[5]Zhang Y,Yan Z,Zhu J,et al.A review of foreign object detection (FOD) for inductive power transfer systems[J].ETransportation,2019(5):1-12.
[6]谭飞刚，翟聪.地铁曲线站台空隙异物自动检测预警系统研究[J].铁路计算机应用，2018,27(6):59-61.
[7]牛宏侠，张肇鑫，宁正，等.铁路轨道异物完整性检测与跟踪算法研究[J].交通运输系统工程与信息，2019,19(1):45-54.
[8]同磊.基于机器视觉的轨道交通线路异物检测技术研究[D].北京：北京交通大学，2012.
[9]李丹丹.铁路轨道异物入侵的智能识别研究[D].兰州：兰州交通大学，2016.
[10]同磊，朱力强，余祖俊，等.基于车载前视摄像机的轨道异物检测[J].交通运输系统工程与信息，2012,12(4):79-83,134.
[11]谭飞刚，余志立，刘开元，等.地铁车门与屏蔽门间缝隙异物自动检测与定位研究[J].深圳信息职业技术学院学报，2023,21(2):78-84.
[12]王前选，李鹏，崔灿，等.轨道交通线路异物入侵的视觉检测方法[J].五邑大学学报(自然科学版),2018,32(3):18-24.
[13]谭飞刚，黄玲，翟聪，等.一种用于大型交通枢纽的跨摄像机行人再识别算法研究[J].铁道学报，2017,39(1):76-82.
[14]谭飞刚.地铁车载单目摄像机下异物侵限检测方法探究[J].深圳信息职业技术学院学报，2021,19(5):71-76.
[15]Dai Y,Liu W.M,Li H,et al.Efficient foreign object detection between PSDs and metro doors via deep neural networks[J].IEEE Access,2020(8):46723-46734.
[16]赵宗扬，康杰虎，吴斌，等.基于FRL-Net的高鲁棒性多尺度小样本轨道入侵异物检测方法研究[J].仪器仪表学报，2024,45(1):239-249.
[17]毛良，邱启盛，刘瑞康，等.基于深度学习的城际高铁轨道交通站台异常检测研究[J/OL].铁道标准设计，1-11.[2024-09-08].https://doi.org/10.13238/j.issn.1004-2954.202308030003.
[18]赵宗扬，康杰虎，梁健，等.基于LGF-Net的全天候轨道入侵异物智能检测系统[J].仪器仪表学报，2023,44(9):287-301.
[19]Ma Y,Yu L,Lin F.T.S.Cross-scale sampling transformer for semantic image segmentation[J].Journal of Intelligent & Fuzzy Systems:Applications in Engineering and Technology,2023,44(2):2895-2907.
[20]Redmon J,Divvala S,Girshick R,et al.You Only Look Once:Unified,Real-Time Object Detection[C]//Proceedings of the lEEE conference on computer vision and pattern recognition,Las Vegas:IEEE,2016:779-788.
[21]Zhao Z.Application of improved CNN-based face detection technology in public administration[J].Journal of computational methods in sciences and engineering,2023,23(4):1985-1997.
[22]Wang H,Dai L,Cai Y,et al.Saliency Detection by Multilevel Deep Pyramid Model[J].Journal of Sensors,2018(3):1-11.
[23]Wan S,Goudos S.Faster R-CNN for Multi-class Fruit Detection using a Robotic Vision System[J].Computer Networks,2019(168):107036.
[24]Ren S.Q,He K.M,Girshick R,et al.Faster R-CNN:Towards Real-Time Object Detection With Region Proposal Networks[J].Advances in neural information processing systems,2015(3):91-99.
[25]Han G,He M,Gao M,et al.Insulator breakage detection based on improved YOLOv5[J].Sustainability,2022,14(10):6066-6083.
[26]Liu W,Anguelov D,Erhan D,et al.SSD:Single Shot Multi-Box Detector[C]// European conference on computer vision,Amsterdam:Springer International Publishing,2016:21-37.
[27]Fu C.Y,Liu W,Rangaa,et al.DSSD:Deconvolutional Single Shot Detector[J].Computer Vision and Pattern Recognition,2017,arXiv:1701.06659.
[28]Li Z,Zhou F.FSSD:Feature Fusion Single Shot Multi-Box Detector[J].Computer Vision and Pattern Recognition,2017,arXiv:1712.00960.
[29]Wang C Y,Bochkovskiy A,Liao H Y M.YOLOv7:Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.Vancouver:IEEE,2023:7464-7475.
[30]Dai Y,Liu W,Wang H,et al.Yolo-former:Marrying yolo and transformer for foreign object detection[J].IEEE Transactions on Instrumentation and Measurement,2022(71):1-14.
[31]蒋伟，梁奕，肖睿，等.基于SDA-SSD的轨道交通异物检测[J].铁道科学与工程学报，2024,21(4):1667-1676.
[32]罗光春，卢显良，张骏，等.基于多传感器数据融合的入侵检测机制[J].电子科技大学学报，2004(1):71-74.
[33]徐田坤，李松峰，李卫军，等.北京地铁异物侵限探测系统研发与实践[J].都市快轨交通，2019,32(5):56-61.
[34]陈仕涛.基于多传感器信息融合的轨道异物检测研究与实现[D].南京：南京邮电大学，2023.
[35]周杏芳.基于多源图像融合的铁路异物侵限检测方法研究[D].北京：北京交通大学，2018.
[36]王楠，侯涛，牛宏侠.多尺度特征融合的铁轨异物入侵检测研究[J].西安交通大学学报，2024,58(9):139-153.
[37]Hou T,Chen Y,Bao C,et al.Railway foreign object tracking based on correlation filtering of optimized regularization model[J].Journal of Applied Science and Engineering,2021,25(2):295-306.
[38]Chen W,Meng S,Jiang Y.Foreign Object Detection in Railway Images Based on an Efficient Two‐Stage Convolutional Neural Network[J].Computational Intelligence and Neuroscience,2022(1):3749635.
基本信息:
DOI：
中图分类号:U298;TP18;TP391.41
引用信息:
[1]谭飞刚.轨道交通轨行区异物自动检测技术研究综述[J].深圳信息职业技术学院学报,2025,23(04):64-69.
基金信息:
深圳信息职业技术学院校级课程思政教育教学改革研究与实践专项(项目编号：2024kcszzx04,2024kcszzx18); 广东省教改课题(项目编号：YJXGLW2022Y33,2023JG372); 深圳市教育科学规划课题(项目编号：yb23052,yb23296)