Journal of Jilin University(Engineering and Technology Edition) ›› 2025, Vol. 55 ›› Issue (4): 1258-1265.doi: 10.13229/j.cnki.jdxbgxb.20240756

Previous Articles     Next Articles

Passenger flow detection method of subway car based on improved YOLO algorithm

Ning GUO1,2(),Xiao-chen HU1,2,De-cun DONG1()   

  1. 1.Key Laboratory of Road and Traffic Engineering，Ministry of Education，Tongji University，Shanghai 201804，China
    2.Shanghai Key Laboratory of Rail Infrastructure Durability and System Safety，Tongji University，Shanghai 201804，China
  • Received:2024-06-12 Online:2025-04-01 Published:2025-06-19
  • Contact: De-cun DONG E-mail:13273031888@163.com;1710910@tongji.edu.cn

RICH HTML

 0   

PDF (PC)

65

Abstract:

During peak hours， the passenger flow of subway carriages increases sharply. In complex scenarios such as dense crowds and target occlusion， it is difficult to accurately identify each passenger， which can easily lead to missed or false detections. To this end， a subway carriage passenger flow detection method based on the improved YOLO algorithm is proposed. After analyzing the YOLOv8 model structure， the TFE module from ASF-YOLO was added to YOLOv8n. Combined with the spatiotemporal model， the characteristics of high passenger flow at stations and low passenger activity during driving， as well as the different flow characteristics of passengers in train doors and carriages， were considered. The multi frame detection results were fused to achieve accurate detection of passenger flow in subway carriages. Through experimental comparison， the average accuracy of the original YOLOv8n model is 57.0%， the improved model is 69.1%， and after multi frame fusion processing， it is 76.6%. The passenger flow information obtained based on this model supports multiple aspects such as passenger travel guidance， emergency rescue support， and railway operation control.

Key words: metro car, YOLOv8 model, passenger flow detection, spatial-temporal model

CLC Number: 

  • U293

Fig.1

YOLOv8 network structure"

Fig.2

TFE module structure"

Fig.3

Carriage space model diagram"

Fig.4

Time division model diagram"

Fig.5

Flow chart of multi frame fusion passenger flowanalysis for optimizing YOLO algorithm"

Fig.6

Example of a single frame image of a carriage video"

Fig.7

Example of detection results"

Fig.8

Passenger flow detection results during non peak travel hours"

Fig.9

Passenger flow detection results during peak travel hours and arrival at stations"

Fig.10

Passenger flow detection results during peak travel periods"

1 Aguilera V, Allio S, Benezech V,et al.Using cell phone data to measure quality of service and passenger flows of Paris transit system[J].Transportation Research Part C: Emerging Technologies, 2014, 43(1):198-211.
2 Zhong G, Wan X, Zhang J,et al.Characterizing passenger flow for a transportation hub based on mobile phone data[J].IEEE Transactions on Intelligent Transportation Systems, 2016, 18(6): 1507-1518.
3 Niu Q, Wu H F, Gao C Y, et al. Laser-based bidirectional pedestrian counting via height map guided regression and voting[J]. Signal, Image and Video Processing, 2017, 11(5): 897-904.
4 余燕. 基于红外CCD与激光测距仪融合的行人检测技术研究[D]. 长春: 吉林大学电子科学与工程学院, 2008.
Yu Yan. Study on the pedestrian detection technology based on the information fusion of infrared CCD and laser measurement system[D]. Changchun: College of Electronic Science and Engineering, Jilin University, 2008.
5 王连震, 王晖, 罗孟德. 基于压力传感器的出租车客流检测系统[J]. 交通科技与经济, 2018, 20(5): 29-31.
Wang Lian-zhen, Wang Hui, Luo Meng-de. A detection system of taxi passenger flow based on pressure sensor[J] Technology & Economy in Areas of Communications, 2018, 20(5): 29-31.
6 Sidenbladh H, Black M J. Learning image statistics for Bayesian tracking[C]∥Proceedings Eighth IEEE International Conference on Computer Vision, Vancouver: Canada, 2001: 709-716.
7 方晨晨, 周继彪, 董升, 等. 基于BP神经网络的地铁车厢拥挤度预测方法[J]. 交通信息与安全, 2018, 36(6): 47-53.
Fang Chen-chen, Zhou Ji-biao, Dong Sheng, et al. A method of forecast congestion of subway carriages based on BP neural network[J]. Journal of Transport Information and Safety, 2018,36(6): 47-53.
8 杨谱. 基于视频图像处理的地铁站拥挤风险预测与人群疏散[D]. 北京: 北京交通大学机械与电子控制工程学院学院, 2018.
Yang Pu. Risk prediction and crowd evacuation of subway station congestion based on video image processing[D]. Beijing: School of Mechanical,Electronic and Control Engineering, Beijing Jiaotong University, 2018.
9 谈世磊, 别雄波, 卢功林, 等. 基于YOLOv5网络模型的人员口罩佩戴实时检测[J]. 激光杂志, 2021, 42(2): 147-150.
Tan Shi-lei, Bie Xiong-bo, Lu Gong-lin, et al. Real time detection of personnel mask wearing based on YOLOv5 network model[J]. Laser Journal, 2021, 42 (2): 147-150.
10 Gao C Q, Li P, Zhang Y J, et al. People counting based on head detection combining Adaboost and CNN in crowded surveillance environment[J]. Neurocomputing, 2016(208): 108-116.
11 Song D, Qiao Y, Corbetta A. Depth driven people counting using deep region proposal network[C]∥IEEE International Conference on Information and Automation(ICIA), Macau,China, 2017: 416-421.
12 Alqahtani F, Banks J, Chandran V,et al.Investigating the efficiency of a three-dimensional facial tracker using stereo camera arrangements[C]∥International Conference on Artificial Intelligence and Big Data,Chengdu,China, 2021: 463-468.
13 Tran C K.Face recognition based on similarity feature-based selection and classification algorithms and wrapper model[J].EJournal Publishing, 2019(3):357-362.
14 Shen G, Jamshidi F, Dong D, et al. Metro pedestrian detection based on mask R-CNN and spatial-temporal feature[C]∥IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP),Shanghai,China, 2020: 173-178.
15 邱芳, 李玉峰, 孔才华. 基于YOLOv5m和注意力机制融合的地铁车厢乘客实时检测[J]. 微处理机, 2022, 43(6): 53-58.
Qiu Fang, Li Yu-feng, Kong Cai-hua. Real-time detection of passengers in subway carriages based on the fusion of YOLOv5m and attention mechanism[J]. Microprocessors, 2022, 43(6): 53-58.
16 Lin S D, Zhu K X, Chen F,et al.Align-Yolact: a one-stage semantic segmentation network for real-time object detection[J].Journal of Ambient Intelligence and Humanized Computing, 2023,14(2):863-870.
17 张馨, 董承梁, 汪晓臣, 等.基于改进YOLOv5s的列车车厢客流密度检测方法研究[J]. 铁路计算机应用, 2022, 31(10): 10-16.
Zhang Xin, Dong Cheng-liang, Wang Xiao-chen, et al. Detection method of passenger flow density in train carriage based on improved YOLOv5s[J]. Railway Computer Application, 2022, 31(10): 10-16.
18 周飞, 郭杜杜, 王洋, 等. 基于改进YOLOv8的交通监控车辆检测算法[J]. 计算机工程与应用, 2024, 60(6): 110-120.
Zhou Fei, Guo Du-du, Wang Yang, et al. Vehicle detection algorithm based on improved YOLOv8 in traffic surveillance[J]. Computer Engineering and Applications,2024,60(6): 110-120.
19 葛雯, 姜添元. 改进YOLO与Deepsort检测跟踪算法的研究[J]. 计算机仿真, 2022, 39(5): 186-190.
Ge Wen, Jiang Tian-yuan. Research on improved YOLO and deepsort detection and tracking algorithms[J].Computer Simulation, 2022, 39(5): 186-190.
[1] Ai-guo LEI,Qi-zhou HU,Xiao-yu WU,Si-yuan QU. Game model of high⁃speed railway delay and passenger choice behavior under incomplete information [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(12): 3496-3504.
[2] Ming-hui YAO,Wei-chao WANG,Qi-liang WU,Yan NIU. Passenger flow prediction of urban public transportation hubs based on real-time data features and XGBoost algorithm [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(11): 3302-3308.
[3] Qing⁃ying LAI,Jun LIU,Ruo⁃yu ZHAO,Yong⁃ji LUO,Ling⁃yun MENG,Ya⁃zhi XU. Optimal trajectory planning for middle⁃to⁃high speed maglev based on dynamic programming with mutative spacing [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(3): 749-756.
[4] MENG Pin-chao, LI Xue-yuan, JIA Hong-fei, LI Yan-zhong. Short-time rail transit passenger flow real-time prediction based on moving average [J]. 吉林大学学报(工学版), 2018, 48(2): 448-453.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] LI Shoutao, LI Yuanchun. Autonomous Mobile Robot Control Algorithm Based on Hierarchical Fuzzy Behaviors in Unknown Environments[J]. 吉林大学学报(工学版), 2005, 35(04): 391 -397 .
[2] Liu Qing-min，Wang Long-shan，Chen Xiang-wei，Li Guo-fa. Ball nut detection by machine vision[J]. 吉林大学学报(工学版), 2006, 36(04): 534 -538 .
[3] Li Hong-ying; Shi Wei-guang;Gan Shu-cai. Electromagnetic properties and microwave absorbing property
of Z type hexaferrite Ba3-xLaxCo2Fe24O41[J]. 吉林大学学报(工学版), 2006, 36(06): 856 -0860 .
[4] Yang Shu-kai, Song Chuan-xue, An Xiao-juan, Cai Zhang-lin . Analyzing effects of suspension bushing elasticity
on vehicle yaw response character with virtual prototype method[J]. 吉林大学学报(工学版), 2007, 37(05): 994 -0999 .
[5] . [J]. 吉林大学学报(工学版), 2007, 37(06): 1284 -1287 .
[6] Che Xiang-jiu，Liu Da-you，Wang Zheng-xuan . Construction of joining surface with G1 continuity for two NURBS surfaces[J]. 吉林大学学报(工学版), 2007, 37(04): 838 -841 .
[7] Liu Han-bing, Jiao Yu-ling, Liang Chun-yu,Qin Wei-jun . Effect of shape function on computing precision in meshless methods[J]. 吉林大学学报(工学版), 2007, 37(03): 715 -0720 .
[8] Zhang Quan-fa，Li Ming-zhe，Sun Gang，Ge Xin . Comparison between flexible and rigid blank-holding in multi-point forming[J]. 吉林大学学报(工学版), 2007, 37(01): 25 -30 .
[9] . [J]. 吉林大学学报(工学版), 2007, 37(04): 0 .
[10] Li Yue-ying，Liu Yong-bing，Chen Hua . Surface hardening and tribological properties of a cam materials[J]. 吉林大学学报(工学版), 2007, 37(05): 1064 -1068 .
Copyright © Journal of Jilin University(Engineering and Technology Edition), All Rights Reserved.
Tel: +86-431-85095297　Fax: +86-431-85094074　E-mail: xbgxb@jlu.edu.cn
Powered by Beijing Magtech Co. Ltd