Research on Signal Lamp Detection for Rail Transport Based on YOLOv8 Algorithm

doi:10.3969/j.issn.1673-4440.2024.09.015

Railway Signalling & Communication Engineering ›› 2024, Vol. 21 ›› Issue (9): 92-98.DOI: 10.3969/j.issn.1673-4440.2024.09.015

Previous Articles Next Articles

Research on Signal Lamp Detection for Rail Transport Based on YOLOv8 Algorithm

Jin Yungong

CRSC International Co., Ltd., Beijing 100070, China

Received:2024-04-15 Revised:2024-09-11 Online:2024-09-25 Published:2024-09-25

基于YOLOv8算法的轨道信号灯检测研究

晋云功

通号国际控股有限公司，北京 100070

作者简介:晋云功（1982—），男，高级工程师，硕士，主要研究方向：铁路信号，邮箱：jinyungong@crsc.cn。

Abstract

Abstract: To improve the intelligence level of signal lamp detection, an intelligent signal lamp detection method based on YOLOv8 algorithm is proposed, which can randomly divide the self built signal lamp dataset into a training set and a validation set in a 4:1 ratio, and train a deep learning model after preprocessing. The results show that the model can converge and achieve end-to-end detection of signal lamp position and color, which has good potential for signal lamp detection tasks.

Key words: signal lamp detection, YOLOv8, deep learning, mean average precision (mAP), intelligent rail transport

摘要： 为提高信号灯检测智能化水平，提出一种基于YOLOv8算法的智能化信号灯检测方法。将自建信号灯数据集按4：1随机划分为训练集和验证集，经预处理后训练深度学习模型。结果显示模型能够收敛，能够端对端地实现信号灯位置及颜色的检测，对信号灯检测任务具有较好的应用潜力。

关键词: 信号灯检测, YOLOv8, 深度学习, 平均精度均值（mAP）, 智能化轨道交通

CLC Number:

U284

Jin Yungong. Research on Signal Lamp Detection for Rail Transport Based on YOLOv8 Algorithm[J]. Railway Signalling & Communication Engineering, 2024, 21(9): 92-98.

晋云功. 基于YOLOv8算法的轨道信号灯检测研究[J]. 铁路通信信号工程技术, 2024, 21(9): 92-98.

Figures/Tables 6

References

[1]张焕增，李茂强，刘英杰.基于视觉的轨道交通信号灯识别算法研究[J].电子制作，2020（18）：53-55.
Zhang Huanzeng, Li Maoqiang, Liu Yingjie. Research on Recognition Algorithm of Rail Transit Traffic Lights Based on Vision[J]. Practical Electronics, 2020(18): 53-55.
[2]李兆龄.城市轨道交通信号系统互联互通的研究[J].铁路通信信号工程技术，2016，13（5）：50-53.
Li Zhaoling. Interoperability of Signal Systems for Urban Rail Transit[J]. Railway Signalling & Communication Engineering, 2016, 13(5): 50-53.
[3]陈坦.以列车为核心的CBTC系统安全防护方法研究[D].北京:北京交通大学，2019.
[4]常峰.全自动限速运行模式方案研究[J].铁路通信信号工程技术，2023，20（4）：63-67.
Chang Feng. Research on Fully Automatic Speed-Restriction Operation Mode[J]. Railway Signalling & Communication Engineering, 2023, 20(4): 63-67.
[5]汪小勇.城市轨道交通基于车车通信的列车自主运行系统探讨[J].中国铁路，2020（9）：77-81.
Wang Xiaoyong. Discussion on Train Autonomous Circumambulate System Based on Vehicleto-Vehicle Communication in Urban Rail Transit[J]. China Railway, 2020(9): 77-81.
[6]郭玉珊，成正波，陈绍文.基于车车通信系统的折返能力研究[J].铁路通信信号工程技术，2021，18（7）：77-80.
Guo Yushan, Cheng Zhengbo, Chen Shaowen. Study on Turn-back Capacity Based on TACS[J]. Railway Signalling & Communication Engineering, 2021, 18(7): 77-80.
[7]张祎.城市轨道交通正线信号灯显示的优化及其点灯电路设计[J].城市轨道交通研究，2020，23（11）：169-171，180.
Zhang Yi. Display Optimization and Lighting Circuit Design for Urban Rail Transit Main Line Signal Lights[J]. Urban Mass Transit, 2020, 23(11): 169-171, 180.
[8]刘爱民.机车信号的故障分析与处理[J].中国新技术新产品，2018（10）：91-92.
Liu Aimin. Fault Analysis and Treatment of Locomotive Signal[J]. New Technology & New Products of China, 2018(10): 91-92.
[9] De Charette R, Nashashibi F. Real Time Visual Traffic Lights Recognition Based on Spot Light Detection and Adaptive Traffic Lights Templates[C]//2009 IEEE Intelligent Vehicles Symposium. Xi’an, China. IEEE, 2009: 358-363.
[10] Omachi M, Omachi S. Detection of Traffic Light Using Structural Information[C]//IEEE 10th International Conference on Signal Processing Proceedings.Beijing, China. IEEE, 2010: 809-812.
[11]谷明琴，蔡自兴，李仪.应用圆形度和颜色直方图的交通信号灯识别[J].计算机工程与设计，2012，33（1）：243-247.
Gu Mingqin, Cai Zixing, Li Yi. Traffic Light Recognition with Circularity and Color Histogram[J]. Computer Engineering and Design, 2012, 33(1): 243-247.
[12]冯霞飞，秦丽娟.基于改进Hough变换的圆形交通信号灯的检测[J].电脑迷，2017（17）：265.
Feng Xiafei, Qin Lijuan. Detection of Circular Traffic Lights Based on Improved Hough Transform[J]. PC Fan, 2017(17): 265.
[13]谭思奇.基于深度学习的道路交通信号灯检测与识别方法研究[D].重庆：重庆交通大学，2022.
[14]邓天民，谭思奇，蒲龙忠.基于改进YOLOv5s的交通信号灯识别方法[J].计算机工程，2022，48（9）：55-62.
Deng Tianmin, Tan Siqi, Pu Longzhong. Traffic Light Recognition Method Based on Improved YOLOv5s[J]. Computer Engineering, 2022, 48(9): 55-62.
[15]李在润，宁芊.基于TTFNet的实时交通信号灯检测[J].现代计算机，2021（17）：118-123.
Li Zairun, Ning Qian. Real-Time Traffic Light Detection Based on TTFNet[J]. Modern Computer, 2021(17): 118-123.
[16]叶嘉欣.基于深度学习的两阶段目标检测算法综述[J].互联网周刊，2023（5）：16-18.
Ye Jiaxin. Overview of Two-Stage Target Detection Algorithms Based on Deep Learning[J]. China Internet Week, 2023(5): 16-18.
[17] 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). Las Vegas, NV, USA. IEEE, 2016: 779-788.
[18]刘瑞锦，何章鸣.基于YOLOv8的卫星遥感图像快速目标检测方法[J].空间控制技术与应用，2023，49（5）：89-97.
Liu Ruijin, He Zhangming. A Fast Target Detection Method for Satellite Remote Sensing Images Based on YOLOv8[J]. Aerospace Control and Application, 2023, 49(5): 89-97.
[19]李松，史涛，井方科.改进YOLOv8的道路损伤检测算法[J].计算机工程与应用，2023，59（23）：165-174.
Li Song, Shi Tao, Jing Fangke. Improved Road Damage Detection Algorithm of YOLOv8[J]. Computer Engineering and Applications, 2023, 59(23): 165-174.
[20]袁红春，陶磊.基于改进的Yolov8商业渔船电子监控数据中鱼类的检测与识别[J].大连海洋大学学报，2023，38（3）：533-542.
Yuan Hongchun, Tao Lei. Detection and Identification of Fish in Electronic Monitoring Data of Commercial Fishing Vessels Based on Improved Yolov8[J]. Journal of Dalian Ocean University, 2023, 38(3): 533-542.
[21]汪友明，徐攀峰.基于改进Adam优化器的CNN电镜医学图像分类[J].西安邮电大学学报，2019，24（5）：26-33.
Wang Youming, Xu Panfeng. CNN Electron Microscope Images Classification Based on Improved Adam Optimizer[J]. Journal of Xi’an University of Posts and Telecommunications, 2019, 24(5): 26-33.

Research on Signal Lamp Detection for Rail Transport Based on YOLOv8 Algorithm

基于YOLOv8算法的轨道信号灯检测研究

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 6

References

Related Articles 3

Recommended Articles

Metrics

Comments

[1]	Zhou Yan. Research and Implementation of Image Detection System for EMU Pantograph Status [J]. Railway Signalling & Communication Engineering, 2023, 20(1): 14-19.
[2]	Yin Zhaojie. Human-computer Interaction-based Deep Learning and Training Data Annotation System [J]. Railway Signalling & Communication Engineering, 2021, 18(8): 24-30.
[3]	Wang Chuanwen, Wang Lei, Huang Renhuan, Qin Rui. Detection Method of Obstacles of Medium-low Speed Train in Transit Based on YOLOv3 Algorithm [J]. Railway Signalling & Communication Engineering, 2021, 18(7): 86-89.