EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Drowsiness Classification in Young Drivers Based on Facial Near-Infrared Images Using a Convolutional Neural Network: A Pilot Study

Ayaka Nomura iD, Atsushi Yoshida, Takumi Torii, Kent Nagumo iD, Kosuke Oiwa iD, Akio Nozawa iD

Sensors · 2025

DOI: 10.3390/s25216755 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Ayaka Nomura und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering and Electronics, Aoyama Gakuin University, Sagamihara 252-5258, Japan. Hauptthemen laut MEDLINE: Automobile Driving, Neural Networks, Computer, Face, Sleep Stages. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Drowsy driving is a major cause of traffic accidents worldwide, and its early detection remains essential for road safety. Conventional driver monitoring systems (DMS) primarily rely on behavioral indicators such as eye closure, gaze, or head pose, which typically appear only after a significant decline in alertness. This study explores the potential of facial near-infrared (NIR) imaging as a hypothetical physiological indicator of drowsiness. Because NIR light penetrates more deeply into biological tissue than visible light, it may capture subtle variations in blood flow and oxygenation near superficial vessels. Based on this hypothesis, we conducted a pilot feasibility study involving young adult participants to investigate whether drowsiness levels could be estimated from single-frame NIR facial images acquired at 940 nm—a wavelength already used in commercial DMS and suitable for both physiological sensitivity and practical feasibility. A convolutional neural network (CNN) was trained to classify multiple levels of drowsiness, and Gradient-weighted Class Activation Mapping (Grad-CAM) was applied to interpret the discriminative regions. The results showed that classification based on 940 nm NIR images is feasible, achieving an optimal accuracy of approximately 90% under the binary classification scheme (Pattern A). Grad-CAM revealed that regions around the nasal dorsum contributed to this, consistent with known physiological signs of drowsiness. These findings support the feasibility of NIR-based drowsiness classification in young drivers and provide a foundation for future studies with larger and more diverse populations.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Automobile DrivingNeural Networks, ComputerFaceSleep StagesHumansPilot ProjectsMaleFemaleAdultYoung AdultSpectroscopy, Near-InfraredConvolutional Neural Networks

Stichwörter der Autor:innen

Grad-CAMconvolutional neural networkdrowsiness classificationfacial near-infrared image

Autor:innen und Institutionen

  • Department of Electrical Engineering and Electronics, Aoyama Gakuin University, Sagamihara 252-5258, Japan.
  • Department of Information and Management Systems Engineering, Nagaoka University of Technology, Niigata 940-2188, Japan.

ORCID-Profile: Ayaka Nomura, Kent Nagumo, Kosuke Oiwa, Akio Nozawa

Zitieren

APA

Nomura, A., Yoshida, A., Torii, T., Nagumo, K., Oiwa, K., & Nozawa, A. (2025). Drowsiness Classification in Young Drivers Based on Facial Near-Infrared Images Using a Convolutional Neural Network: A Pilot Study. Sensors. https://doi.org/10.3390/s25216755

Vancouver

Nomura A, Yoshida A, Torii T, Nagumo K, Oiwa K, Nozawa A. Drowsiness Classification in Young Drivers Based on Facial Near-Infrared Images Using a Convolutional Neural Network: A Pilot Study. Sensors. 2025. doi:10.3390/s25216755

BibTeX
@article{Nomura2025,
  author = {Nomura, Ayaka and Yoshida, Atsushi and Torii, Takumi and Nagumo, Kent and Oiwa, Kosuke and Nozawa, Akio},
  title = {Drowsiness Classification in Young Drivers Based on Facial Near-Infrared Images Using a Convolutional Neural Network: A Pilot Study},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25216755}
}
Kostenlos starten →