Answers are grounded in this paper and cite their sources.
This research demonstrates a real-time helmet detection system using YOLOv8 and Streamlit, indicating improved safety compliance for motorcyclists.
The high rate of traffic accidents involving motorcyclists is often caused by negligence in using safety equipment such as helmets. This study aims to design an automatic helmet detection system by utilizing the YOLOv8 (You Only Look Once version 8) object detection algorithm. The dataset was sourced from Roboflow and categorized into two classes: "wearing a helmet" and "not wearing a helmet." The training process was carried out on Google Colab using a GPU and integrated into a web-based application via Streamlit, which is capable of detecting both static images and real-time video. The trained model achieved a mAP@0.5 score of 88.8%, indicating a high detection performance. This system is expected to be applicable for monitoring safety compliance on roads and in work environments.y Look Once versi 8). Data yang digunakan diambil dari Roboflow dan diklasifikasikan menjadi dua kategori, yaitu "pakai helm" dan "tanpa helm". Proses pelatihan dilakukan di Google Colab menggunakan GPU, kemudian diintegrasikan ke dalam aplikasi berbasis web melalui Streamlit yang dapat mendeteksi baik gambar statis maupun video secara langsung. Model yang dibangun memperoleh nilai mAP@0.5 sebesar 88.8%, menandakan performa deteksi yang cukup tinggi. This system is expected to be applicable for monitoring safety compliance on roads and in work environments.
No takes yet. Share an insight, caveat, or question.
Munip et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: