Performance Evaluation of YOLOv8 Model in Motorcycle Helmet Violation Detection System Using Traffic Image Dataset

DOI

10.2991/978-94-6239-805-4_14How to use a DOI?

Keywords

Computer Vision; Deep Learning; Helmet Violation; Intelligent Traffic System; YOLOv8

Abstract

The high number of motorcycle users in developing countries is often followed by an increase in traffic violations, specifically the failure to wear helmets, which significantly contributes to head injury risks. This study aims to evaluate the performance of the YOLOv8 model in detecting motorcycle helmet violations using a traffic image dataset. The research methodology encompasses data collection, image annotation, pre-processing, YOLOv8 model training, and performance evaluation using precision, recall, F1-score, and mean Average Precision (mAP). The experimental results demonstrate that the YOLOv8 model achieved an accuracy of 87.93%, precision of 90.32%, recall of 89.44%, F1-score of 90.37%, and mAP@0.5 of 87.80%. These results indicate that the YOLOv8 model is effective for real-time automated helmet violation detection. This research provides a robust contribution to intelligent traffic monitoring systems and serves as practical instructional material for computer vision courses. Through advanced deep learning techniques, this technological approach helps law enforcement agencies reduce accidents and monitor roads efficiently every day by providing accurate and reliable automated analysis of modern traffic camera feeds. Furthermore, future developments could integrate edge computing devices to enable instant alerts for officers on duty, thereby minimizing human error and enhancing overall public safety measures across urban transportation networks in real time.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - I Putu Astya Prayudha
AU  - Ni Gusti Ayu Putu Harry Saptarini
AU  - Gde Brahupadhya Subiksa
PY  - 2026
DA  - 2026/10/08
TI  - Performance Evaluation of YOLOv8 Model in Motorcycle Helmet Violation Detection System Using Traffic Image Dataset
BT  - Proceedings of the International Conference on Sustainable Green Tourism Applied Science - Engineering Applied Science 2026 (ICOSTAS-EAS 2026)
PB  - Atlantis Press
SP  - 129
EP  - 136
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-805-4_14
DO  - 10.2991/978-94-6239-805-4_14
ID  - Prayudha2026
ER  -