Research on the Application of Electric Vehicle Recognition in Lifts Based on Yolov8 Model

Xuanjie Xu; Shuxiang Yang; Haoran Shu

doi:10.54097/9e6t0280

Authors

Xuanjie Xu
Shuxiang Yang
Haoran Shu

DOI:

https://doi.org/10.54097/9e6t0280

Keywords:

YOLOv8; Electric bicycle; Lift safety; Risky behaviour detection.

Abstract

The behaviour of electric bicycle into the lift is a great security risk, but also one of the causes of many fires in the building, bringing a serious threat to people's life and property safety. In this paper, we use YOLOv8 model to identify and detect e-bikes in the lift scene. Compared to YOLOv5, YOLOv8 improves performance and employs an anchor-free mechanism, reducing hyperparameter tuning complexity and enhancing small object detection in elevator scenarios. The experimental test results show that: the mAP@50 reaches 87%, and the operating speed reaches 125 FPS, which meets the deployment requirements of the actual monitoring system. This study provides a new solution in the field of lift safety monitoring, which can significantly improve the efficiency of detecting e-bikes in lifts and prevent safety accidents such as fires caused by e-bikes.

Downloads

Download data is not yet available.

References

[1] Bigan He. Research and implementation of real-time detection system for electric vehicles in lifts based on improved YOLOv5 [D]. South China University of Technology, 2023.

[2] Yuyang Li, Jiquan Shen, Haixia Zhai, et al. Mask wearing detection algorithm based on improved SSD[J]. Computer Engineering, 2022, 48(08): 173-179+186.

[3] Xin Wang, Yinan Feng. Helmet-wearing detection for cyclists based on improved SSD[J]. Electronic Measurement Technology, 2022, 45(21): 90-97.

[4] Hongcheng Zhao, Ziyang Zhang, Yu Song. [Research on the design of alarm system for electric vehicle intrusion into lift [J]. Fire Protection World (Electronic Edition), 2023, 9 (15): 63-65.

[5] Ziyu Ma. Research on recognition of electric vehicles entering car based on neural network and evidence theory[D]. Zhengzhou University, 2021.

[6] Lin Chen, Chuanjing Chen, Peng Zhang. YOLOv4-tiny based electric vehicle detection model in lifts [J]. Value Engineering, 2022, 41 (12): 117-119.

[7] Bigan He. Lift car electric vehicle banning system based on deep learning and edge computing technology [J]. China Elevator, 2023, 34(11): 15-19+22.

[8] Qiaorun Lu, Hui Lin, Xiaowei Liu. Design of OR-CNN-based dangerous behaviour detection system for electric vehicles entering lifts [J]. Electromechanical Engineering Technology, 2024, 53 (01): 253-256.

[9] Suguang Zhang, Wentao Zhang, Yang Liu, et al. Improved MobileNet-SSD for electric vehicle recognition in lifts [J]. Mechanical Design and Manufacturing, 2024, (09): 340-345.

[10] Yuna Liu, Shuangbao Ma. Lightweight fabric defect detection algorithm based on improved YOLOv8n [J/OL]. Journal of Guangxi Normal University (Natural Science Edition), 1-12 [2024-11-14].

[11] Zhen Liu, Xianzhao Yang, Yang Chen, et al. Target detection algorithm for foggy weather based on improved YOLOv8s [J/OL]. Electronic Measurement Technology, 1-9 [2024-11-14].

[12] Haiqun Wang, Peixu Wei, Haolong Xie, et al. Infrared ship detection based on improved YOLOv8[J/OL]. Electro-Optics and Control, 1-8 [2024-11-14].

[13] Yaoming Ma, Pengfei Zhang, Fusheng Tan. Improved YOLOv8s algorithm for smoke flame detection in complex background [J/OL]., 1-13 [2024-11-14].

[14] Boyuan Wang, Fei Kang, Xuewen Liang, et al. Improved YOLOv8s-based method for identifying surface personnel and seepage in earth and rock dams [J/OL]. 1-13 [2024-11-14].