A Real-Time Deep Learning Solution for Helmetless Rider Detection in Urban Traffic

View at publisher Summarise with VIRAT
Authors: Archana S, Vishesha R, Janani C, Praveen Kumar K, Rajan C
Cited by: 0
References: 18

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Road accidents involving two-wheeler riders remain a critical concern worldwide, with a significant number of fatalities caused by the neglect of wearing helmets. Manual surveillance to enforce helmet regulations is inefficient and prone to human oversight. This study presents a smart helmet detection framework that employs deep learning-based real-time object recognition to identify riders not wearing helmets. The proposed approach utilises the YOLOv8 (You Only Look Once, version 8) model to precisely detect riders, helmets, and motorcycles from both live video feeds and static imagery. By analysing the spatial relationship between detected helmets and riders, the system classifies whether a rider is helmeted or helmetless. The experimental results demonstrate high detection accuracy and efficient frame processing, proving the model's capability for real-time traffic monitoring. The developed system can be integrated into smart city infrastructure to assist traffic authorities in improving road safety and ensuring law enforcement compliance.

Fields of Study & Subjects

Advanced Neural Network Applications Video Surveillance and Tracking Methods IoT and GPS-based Vehicle Safety Systems

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
1–8
Publication date
21 January 2026
Language
EN