Modeling and application of road intersections based on digital twins

doi:10.3969/j.issn.1674-8484.2023.01.007

Abstract

Abstract:

A digital twin traffic management system at road intersection was established to effectively regulate the traffic state of the road network. The core elements and theoretical system of the digital twin model of road intersection were described from six aspects: the theory and the model construction, assembly, integration, management, verification and correction. The operation mechanism of the model and the key technologies of real-time interaction between man, vehicle, road and environment were analyzed from two aspects of the traffic element management and the operation process control. The traffic elements and the intersection operation status were identified in real time based on machine vision; The construction technology was analyzed for the management system based on “virtual control reality”. The results show that this method can accurately identify and simulate the traffic elements and operation state of the road intersection, create a digital window for relevant departments to efficiently adjust the traffic state of the road network, and provide data support for automatic driving.

Key words: intelligent transportation, traffic management system, digital twins, road intersection, virtual control of reality, machine vision

CLC Number:

TP391.9

ZHANG Hong, YU Hailiang, ZHENG Zan, YUAN Shengdong, XIONG Guoqiang. Modeling and application of road intersections based on digital twins[J]. Journal of Automotive Safety and Energy, 2023, 14(1): 55-61.

Figures/Tables 12

References 14

[1]	陶飞, 刘蔚然, 张萌, 等. 数字孪生五维模型及十大领域应用[J]. 计算机集成制造系统, 2019, 25(1): 1-18.
	TAO Fei, LIU Weiran, ZHANG Meng, et al. Five-dimensional digital twin model and its ten applications[J]. Comput Integr Manuf Syst, 2019, 25(1): 1-18. (in Chinese)
[2]	陶飞, 程颖, 程江峰, 等. 数字孪生车间信息物理融合理论与技术[J]. 计算机集成制造系统, 2017, 23(8): 1603-1611.
	TAO Fei, CHENG Ying, CHENG Jiangfeng, et al. Theories and technologies for cyber-physical fusion in digital twin shopfloor[J]. Comput Integr Manuf Syst, 2017, 23(8): 1603-1611. (in Chinese)
[3]	LU Yuqian, LIU Chao, XU Xun, et al. Digital Twin-driven smart manufacturing: Connotation, reference model, applications and research issues[J]. Robot CIM-INT Manuf, 2020, 61: 101837. doi: 10.1016/j.rcim.2019.101837 URL
[4]	伍朝辉, 刘振正, 石可, 等. 交通场景数字孪生构建与虚实融合应用研究[J]. 系统仿真学报, 2021, 33(2): 295-305. doi: 10.16182/j.issn1004731x.joss.20-0754
	WU Zhaohui, LIU Zhenzheng, SHI Ke, et al. Review on the construction and application of digital twins in transportation scenes[J]. J Syst Simul, 2021, 33(2): 295-305. (in Chinese) doi: 10.16182/j.issn1004731x.joss.20-0754
[5]	Park K T, Nam Y W, Lee H S, et al. Design and implementation of a digital twin application for a connected micro smart factory[J]. Int J Comput Integ M, 2019, 32(6): 596- 614.
[6]	ZHANG Ke, CAO Jiayu, ZHANG Yan. Adaptive digital twin and multiagent deep reinforcement learning for vehicular edge computing and networks[J]. IEEE Trans Indu Info, 2022, 18(2): 1405-1413.
[7]	陶飞, 张贺, 戚庆林, 等. 数字孪生模型构建理论及应用[J]. 计算机集成制造系统, 2021, 27(01): 1-15.
	TAO Fei, ZHANG He, QI Qinglin, et al. Theory of digital twin modeling and its application[J]. Comput Integr Manuf Syst, 2021, 27(1): 1-15. (in Chinese) doi: 10.13196/j.cims.2021.01.001
[8]	Jones D, Snider C, Nassehi A, et al. Characterising the digital twin: A systematic literature review[J]. Cirp J Manuf Sci Tech, 2020, 29: 36-52. doi: 10.1016/j.cirpj.2020.02.002 URL
[9]	LI Guofa, LIN Siyan, LI Shen, et al. Learning automated driving in complex intersection scenarios based on camera sensors: A deep reinforcement learning approach[J]. IEEE Sensors J, 2022, 22(5): 4687-4696. doi: 10.1109/JSEN.2022.3146307 URL
[10]	Jubayer F, Soeb J A, Mojumder A, et al. Detection of mold on the food surface using YOLOv5[J]. Curr Res Food Sci, 2021, 4: 724-728. doi: 10.1016/j.crfs.2021.10.003 URL
[11]	ZHOU Junchi, JIANG Ping, ZOU Airu, et al. Ship target detection algorithm based on improved YOLOv5[J]. J Marine Sci Eng, 2021, 9(8): 908-908. doi: 10.3390/jmse9080908 URL
[12]	XU Xiaowo, ZHANG Xiaoling, ZHANG Tianwen. Lite-YOLOv5: A lightweight deep learning detector for on-board ship detection in large-scene Sentinel-1 SAR images[J]. Remote Sens-Basel, 2022, 14(4): (Paper No)1018.
[13]	LIN Ciyun, GUO Yingzhi, LI Wenjun, et al. An automatic lane marking detection method with low-density roadside LiDAR data[J]. IEEE Sensors J, 2021, 21(8) :10029-10038.
[14]	QIN Fei, BU Xiangxi, ZENG Zhiyuan, et al. Small target detection for FOD millimeter-wave radar based on compressed imaging[J]. IEEE Geosci Remote Sen Lett, 2022, 19: 1-5.

测试版本	YOLOv5
网络模型	YOLOv5l.pt
模型深度	1.0
模型广度	1.0
NMS置信度	0.45
置信度	0.15

测试版本	YOLOv5
网络模型	YOLOv5l.pt
模型深度	1.0
模型广度	1.0
NMS置信度	0.45
置信度	0.15