基于YOLO v3的有轨电车在途障碍物检测方法

doi:10.3969/j.issn.1673-4440.2021.11.011

铁路通信信号工程技术 ›› 2021, Vol. 18 ›› Issue (11): 51-55.DOI: 10.3969/j.issn.1673-4440.2021.11.011

基于YOLO v3的有轨电车在途障碍物检测方法

马永刚，吴凯，谢文斌

通号万全信号设备有限公司，杭州 310018

收稿日期:2020-08-27 修回日期:2021-09-14 出版日期:2021-11-25 发布日期:2021-11-25

YOLO v3-based Obstacle Detection Method for Tram in Transit

Ma Yonggang, Wu Kai, Xie Wenbin

CRSC Wanquan Signal Equipment Co., Ltd., Hangzhou 310018, China

Received:2020-08-27 Revised:2021-09-14 Online:2021-11-25 Published:2021-11-25

摘要/Abstract

摘要： 有轨电车一般使用混合路权，与社会车辆接触密切，安全性需进一步提升。以视觉传感器与YOLO v3卷积神经网络为基础，通过对YOLO v3网络模型损失函数的优化，提出一种准确率较高的有轨电车在途障碍物识别方法，实时识别列车运行图中可能遇到的各种危险因素，辅助司机驾驶，提升车辆运行安全性。经过验证，本方法具有较高的准确性和鲁棒性，是一种有效的列车驾驶辅助手段。

关键词: YOLO v3, 障碍物检测, 有轨电车

Abstract: Trams generally use mixed right-of-way and are in close contact with automobiles, safety still needs to be further improved. Based on the vision sensor and YOLO v3 convolutional neural network, this paper proposes a method to identify the obstacles of a tram in transit with high accuracy by optimizing the loss function of YOLO v3 network model, and carries out the identification of various risk factors that may be encountered in the train diagram to assist the driver and improve operation safety. It is proved that this method has high accuracy and robustness, and is an effective train driving aid means.

Key words: YOLO v3, obstacle detection, tram

中图分类号:

U239.5

马永刚, 吴凯, 谢文斌. 基于YOLO v3的有轨电车在途障碍物检测方法[J]. 铁路通信信号工程技术, 2021, 18(11): 51-55.

Ma Yonggang, Wu Kai, Xie Wenbin. YOLO v3-based Obstacle Detection Method for Tram in Transit[J]. Railway Signalling & Communication Engineering, 2021, 18(11): 51-55.

图/表 3

参考文献

[1]臧宇，许广鹏，关和宁，等.国内现代有轨电车车辆发展状况综述[J].现代城市轨道交通，2016(2):1-6.
Zang Yu, Xu Guangpeng, Guan Hening, et al. Introduction of Development of Modern Tram in China[J]. Modern Urban Transit, 2016(2): 1-6.
[2]郭磊，李克强，王建强，等.一种基于特征的车辆检测方法[J].汽车工程，2006，28(11):1031-1035.
Guo Lei, Li Keqiang, Wang Jianqiang, et al. A Feature-Based Vehicle Detection Method[J].Automotive Engineering, 2006, 28(11): 1031-1035.
[3] Jazayeri A, Cai Hongyuan, Zheng Jiang yu, et al. Vehicle Detection and Tracking in Car Video Based on Motion Model[J].IEEE Transactions on Intelligent Transportation Systems, 2011, 12(2): 583-595.
[4] Tehrani Niknejad H, Takeuchi A, Mita S, et al. On-Road Multivehicle Tracking Using Deformable Object Model and Particle Filter with Improved Likelihood Estimation[J]. IEEE Transactions on Intelligent Transportation Systems, 2012, 13(2): 748-758.
[5]王斌.基于深度学习的行人检测[D].北京:北京交通大学，2015.
[6]刘芷含.基于深度学习的行人目标检测方法[D].南京:南京理工大学，2018.
[7]胡超超，刘军，张凯，等.基于深度学习的行人和骑行者目标检测及跟踪算法研究[J].汽车技术，2019(7):19-23.
Hu Chaochao, Liu Jun, Zhang Kai, et al. Research on Target Detection and Tracking of Pedestrian and Cyclist Based on Deep Learning[J]. Automobile Technology, 2019(7): 19-23.
[8]黄皓宇.基于Mask R-CNN的街景车辆目标的检测方法研究与应用[D].武汉:华中师范大学，2019.
[9]刘敦强.基于Faster RCNN的道路车辆检测算法研究[D].南京:南京航空航天大学，2018.
[10]王宇宁，庞智恒，袁德明.基于YOLO算法的车辆实时检测[J].武汉理工大学学报，2016，38(10):41-46.
Wang Yuning, Pang Zhiheng, Yuan Deming.Vehicle Detection Based on YOLO in Real Time[J]. Journal of Wuhan University of Technology, 2016, 38(10): 41-46.
[11]卞山峰，张庆辉.基于改进YOLO v2的车辆实时检测算法[J].电子质量，2019(10):19-22.
Bian Shanfeng, Zhang Qinghui. Real-Time Vehicle Detection Algorithm Based on Improved YOLO v2[J]. Electronics Quality, 2019(10): 19-22.
[12]祝庆发，陈永生，郭玉臣.基于改进YOLO算法的密集人群场景下的行人检测[J].电脑知识与技术，2019，15(22):175-176.
[13]王玺坤，姜宏旭，林珂玉.基于改进型YOLO算法的遥感图像舰船检测[J].北京航空航天大学学报，2020，46(6):1184-1191.
Wang Xikun, Jiang Hongxu, Lin Keyu. Remote Sensing Image Ship Detection Based on Modified YOLO Algorithm[J]. Journal of Beijing University of Aeronautics and Astronautics, 2020, 46(6): 1184-1191.
[14]鞠默然，罗海波，王仲博，等.改进的YOLO V3算法及其在小目标检测中的应用[J].光学学报，2019，39(7):253-260.
Ju Moran, Luo Haibo, Wang Zhongbo, et al. Improved YOLO V3 Algorithm and Its Application in Small Target Detection[J]. Acta Optica Sinica, 2019, 39(7): 253-260.
[15]王钏文,王磊,黄仁欢，等.基于YOLO v3算法的中低速列车在途障碍物检测方法[J].铁路通信信号工程技术，2021，18(7):86-89.
Wang Chuanwen, Wang Lei, Huang Renhuan,et al. Detection Method of Obstacles of Medium-Low Speed Train in Transit Based on YOLO v3 Algorithm[J].Railway Signalling & Communication Engineering, 2021, 18(7):86-89.
[16] Redmon J, Divvala S, Girshick R, et al. You Only Look Once: Unified, Real-Time Object Detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). June 27-30, 2016, Las Vegas, NV, USA.IEEE, 2016: 779-788.
[17] Rezatofighi H, Tsoi N, Gwak J, et al. Generalized Intersection over Union: a Metric and a Loss for Bounding Box Regression[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 15-20, 2019, Long Beach, CA, USA. IEEE, 2019: 658-666.
[18] Abadi M, Agarwal A, Barham P, et al. TensorFlow:Large-Scale Machine Learning on Heterogeneous Distributed Systems[EB/OL].（2016-03-16）[2020-08-27]. http://arxiv.org/abs/1603.04467.

基于YOLO v3的有轨电车在途障碍物检测方法

YOLO v3-based Obstacle Detection Method for Tram in Transit

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 3

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	王钏文, 王磊, 黄仁欢, 覃锐. 基于YOLOv3算法的中低速列车在途障碍物检测方法[J]. 铁路通信信号工程技术, 2021, 18(7): 86-89.
[2]	姚文华, 侯锡立, 贾云光, 宋凤娟. 有轨电车信号控制系统技术方案[J]. 铁路通信信号工程技术, 2021, 18(4): 59-63.
[3]	杨峥岭, 杨建华, 刘尧, 张楠, 杨普. 有轨电车专用轨道电路（ITCM-100型）工程应用研究[J]. 铁路通信信号工程技术, 2021, 18(12): 89-94.
[4]	金晓雷, 陈哲, 江兴林. 现代有轨电车正线道岔控制子系统雷电防护设计[J]. 铁路通信信号工程技术, 2021, 18(12): 99-102.
[5]	闫学祥. 有轨电车自动驾驶技术应用简析[J]. 铁路通信信号工程技术, 2021, 18(1): 60-65.