Vehicle Recognition and Driving Information Detection with UAV Video Based on Improved YOLOv5-DeepSORT Algorithm
Sensors · 28.04.2025 · 25 (9) · 2788
DOI: 10.3390/s25092788 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 28.04.2025. Verfasst von Binshuang Zheng und 4 weiteren Autor:innen. Beteiligte Einrichtung: Research and Development Center of Transport Industry of New Generation of Artificial Intelligence Technology, Zhejiang Scientific Research Institute…. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Open Project of Research and Development Center of Transport Industry of New Generation of Artificial Intelligence Technology, Graduate Research Innovation Project in Jiangsu Province, Natural Science Research General Project of Colleges and Universities in Jiangsu Province.
Abstract (Originalsprache)
To investigate whether the skid resistance of the ramp meets the requirements of vehicle driving safety and stability, the simulation using the ideal driver model is inaccurate. Therefore, considering the driver’s driving habits, this paper proposes the use of Unmanned aerial vehicles (UAVs) for the collection and extraction of vehicle driving information. To process the collected UAV video, the Google Collaboration platform is used to modify and compile the “You Only Look Once” version 5 (YOLOv5) algorithm with Python 3.7.12, and YOLOv5 is retrained with the captured video. The results show that the precision rate P and recall rate R have satisfactory results with an F1 value of 0.86, reflecting a good P-R relationship. The loss function also stabilized at a very low level after 70 training epochs. Then, the trained YOLOv5 is used to replace the Faster R-CNN detector in the DeepSORT algorithm to improve the detection accuracy and speed and extract the vehicle driving information from the perspective of UAV. By coding, the coordinate information of the vehicle trajectory is extracted, the trajectory is smoothed, and the frame difference method is used to calculate the real-time speed information, which is convenient for the establishment of a real driver model.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Research and Development Center of Transport Industry of New Generation of Artificial Intelligence Technology, Zhejiang Scientific Research Institute of Transport, No. 705 Dalongjuwu Rd., Hangzhou 311305, China.
- School of Modern Posts, Nanjing University of Posts and Telecommunications, Nanjing 210023, China.
- China State Construction Engineering (Hong Kong) Limited, Hong Kong 999077, China.
- School of Transportation, Southeast University, Nanjing 211189, China.
- National Demonstration Center for Experimental Education of Road and Traffic Engineering, Southeast University, Nanjing 211189, China.
ORCID-Profile: Binshuang Zheng, Jing Zhou, Zhengqiang Hong, Xiaoming Huang
Förderung
- Open Project of Research and Development Center of Transport Industry of New Generation of Artificial Intelligence Technology
- Graduate Research Innovation Project in Jiangsu Province
- Natural Science Research General Project of Colleges and Universities in Jiangsu Province
- National Key R&D Program of China
Zitieren
APA
Zheng, B., Zhou, J., Hong, Z., Tang, J., & Huang, X. (2025). Vehicle Recognition and Driving Information Detection with UAV Video Based on Improved YOLOv5-DeepSORT Algorithm. Sensors, 25(9), 2788. https://doi.org/10.3390/s25092788
Vancouver
Zheng B, Zhou J, Hong Z, Tang J, Huang X. Vehicle Recognition and Driving Information Detection with UAV Video Based on Improved YOLOv5-DeepSORT Algorithm. Sensors. 2025;25(9):2788. doi:10.3390/s25092788
BibTeX
@article{Zheng2025,
author = {Zheng, Binshuang and Zhou, Jing and Hong, Zhengqiang and Tang, Junyao and Huang, Xiaoming},
title = {Vehicle Recognition and Driving Information Detection with UAV Video Based on Improved YOLOv5-DeepSORT Algorithm},
journal = {Sensors},
year = {2025},
volume = {25},
number = {9},
pages = {2788},
doi = {10.3390/s25092788}
}
EUVIMED