Vision Transformer-Based Driver Fatigue Detection in Real-Time Embedded Systems
Yazarlar (5)
Dr. Öğr. Üyesi Zehra ELMI Beykoz Üniversitesi, Türkiye
Arş. Gör. Firdevs EYİDOĞAN Beykoz Üniversitesi, Türkiye
Zeynep Sena Kaya
İstanbul Sabahattin Zaim University, Türkiye
İstanbul Sabahattin Zaim University, Türkiye
Ali Buğuş
İstanbul Sabahattin Zaim University, Türkiye
İstanbul Sabahattin Zaim University, Türkiye
Soheila Elmi
Koç University, Türkiye
Koç University, Türkiye
| Makale Türü |
Özgün Makale
(ESCI dergilerinde yayınlanan tam makale)
|
||
| Dergi Adı | International Journal of Intelligent Transportation Systems Research | ||
| Dergi ISSN | 1348-8503 Dergi Bilgileri (2026) | ||
| Dergi Tarandığı Indeksler | ESCI | ||
| Makale Dili | İngilizce | Basım Tarihi | 05-2026 |
| Kabul Tarihi | 06-05-2026 | Yayınlanma Tarihi | 29-05-2026 |
| Cilt / Sayı / Sayfa | 0 / 1 / 1–12 | DOI | 10.1007/s13177-026-00673-2 |
| Makale Linki | https://doi.org/10.1007/s13177-026-00673-2 | ||
| UAK Araştırma Alanları |
|
||
| Özet |
| Driver fatigue is a major contributor to traffic accidents, yet reliable early warning remains challenging under real-world and embedded constraints. This study presents a camera-only driver-fatigue detection pipeline that couples lightweight face tracking (MediaPipe) with a single Vision Transformer (ViT) classifier ( 86M parameters) to infer alert vs. drowsy states from facial cues. The model is trained on a multi-source dataset of 4,000 images aggregated from seven public fatigue datasets and evaluated on a held-out test split, achieving 95.0% accuracy, 93.8% F1-score, and ROC-AUC of 0.986. On Raspberry Pi 5, end-to-end inference runs at 55.6 ms/frame (18.0 FPS). Compared with a detection-driven YOLO baseline using the same labeling protocol and test split, the proposed ViT improves accuracy (95.0% vs. 93.2%) and ROC-AUC (0.986 vs. 0.979) while trading throughput (18.0 vs. 28.0 FPS), clarifying the … |
| Anahtar Kelimeler |
| Driver fatigue | Image processing | Vision transformer | Real-time systems | Traffic safety | Deep learning |
BM Sürdürülebilir Kalkınma Amaçları
| Atıf Sayıları | |
| Scopus | 1 |
| Google Scholar | 1 |