EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing Driver Monitoring Systems Based on Novel Multi-Task Fusion Algorithm

Romas Vijeikis iD, Ibidapo Dare Dada iD, Adebayo A Abayomi-Alli iD, Vidas Raudonis

Sensors · 06.11.2025 · 25 (21) · 6799

DOI: 10.3390/s25216799 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 06.11.2025. Verfasst von Romas Vijeikis und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Automation, Faculty of Electrical and Electronic Engineering, Kaunas University of Technology, 51367 Kaunas, Lithuania. Hauptthemen laut MEDLINE: Algorithms, Accidents, Traffic, Automobile Driving. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Distracted driving continues to be a major contributor to road accidents, highlighting the growing research interest in advanced driver monitoring systems for enhanced safety. This paper seeks to improve the overall performance and effectiveness of such systems by highlighting the importance of recognizing the driver’s activity. This paper introduces a novel methodology for assessing driver attention by using multi-perspective information using videos that capture the full driver body, hands, and face and focusing on three driver tasks: distracted actions, gaze direction, and hands-on-wheel monitoring. The experimental evaluation was conducted in two phases: first, assessing driver distracted activities, gaze direction, and hands-on-wheel using a CNN-based model and videos from three cameras that were placed inside the vehicle, and second, evaluating the multi-task fusion algorithm, considering the aggregated danger score, which was introduced in this paper, as a representation of the driver’s attentiveness based on the multi-task data fusion algorithm. The proposed methodology was built and evaluated using a DMD dataset; additionally, model robustness was tested on the AUC_V2 and SAMDD driver distraction datasets. The proposed algorithm effectively combines multi-task information from different perspectives and evaluates the attention level of the driver.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsAccidents, TrafficAutomobile DrivingHumansDatasets as TopicMultitasking BehaviorNeural Networks, ComputerAttentionYoung AdultAdultMiddle Aged

Stichwörter der Autor:innen

computer visiondeep learningdriver activity recognitiondriver attention analysisdriver monitoringmulti-perspective learningmulti-task fusionroad safetyvideo classification

Autor:innen und Institutionen

  • Department of Automation, Faculty of Electrical and Electronic Engineering, Kaunas University of Technology, 51367 Kaunas, Lithuania.
  • Department of Computer and Information Science, Covenant University, Ota 112104, Nigeria.
  • Department of Computer Science, Federal University of Agriculture, Abeokuta 110124, Nigeria.
  • Department of Software Engineering and Information Systems, Federal University of Agriculture, Abeokuta 110124, Nigeria.
  • Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), 4200-464 Porto, Portugal.

ORCID-Profile: Romas Vijeikis, Ibidapo Dare Dada, Adebayo A Abayomi-Alli

Zitieren

APA

Vijeikis, R., Dada, I. D., Abayomi-Alli, A. A., & Raudonis, V. (2025). Enhancing Driver Monitoring Systems Based on Novel Multi-Task Fusion Algorithm. Sensors, 25(21), 6799. https://doi.org/10.3390/s25216799

Vancouver

Vijeikis R, Dada ID, Abayomi-Alli AA, Raudonis V. Enhancing Driver Monitoring Systems Based on Novel Multi-Task Fusion Algorithm. Sensors. 2025;25(21):6799. doi:10.3390/s25216799

BibTeX
@article{Vijeikis2025,
  author = {Vijeikis, Romas and Dada, Ibidapo Dare and Abayomi-Alli, Adebayo A and Raudonis, Vidas},
  title = {Enhancing Driver Monitoring Systems Based on Novel Multi-Task Fusion Algorithm},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {21},
  pages = {6799},
  doi = {10.3390/s25216799}
}
Kostenlos starten →