| Issue |
ITM Web Conf.
Volume 78, 2025
International Conference on Computer Science and Electronic Information Technology (CSEIT 2025)
|
|
|---|---|---|
| Article Number | 03008 | |
| Number of page(s) | 8 | |
| Section | Intelligent Systems and Computing in Industry, Robotics, and Smart Infrastructure | |
| DOI | https://doi.org/10.1051/itmconf/20257803008 | |
| Published online | 08 September 2025 | |
Research on The Vehicle Detection Technology Based on The Yolo Model
Guangzhou Maritime University, Guangzhou, Guangdong, 510725, China
Vehicle detection is the most basic and important part of intelligent transportation systems and vehicle driving technology. Vehicle detection is mainly responsible for finding all vehicles in a given image and giving their bounding boxes. From the point of view of safety and practicality, vehicle detectors need to have very high detection accuracy and be able to complete real-time processing. Based on PASCAL VOC data set, this paper explores the application of YOLO target detection algorithm in the vehicle detection field. The convolutional neural network is trained by gradient descent method and tested with the same test set. On the test set, the vehicle detection algorithm mAP based on YOLO implementation is 70.3%, and the detection speed is 80.7FPS. According to the research results, the vehicle detection algorithm based on YOLO has reached the standard of real-time processing, but the detection effect of small and dense car targets is poor.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.