Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jul 16, 2026

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research
07:15

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Published on: December 18, 2020

Emotion-Aware Contextual Modelling for Robust Driver Fatigue Detection.

Sebastian Budzan1, Roman Wyżgolik1

  • 1Department of Measurements and Control Systems, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland.

Sensors (Basel, Switzerland)
|July 15, 2026
PubMed
Summary

This study introduces a new driver fatigue detection system using facial cues, behavior, and emotions. It achieves 94% accuracy, offering a more reliable way to monitor driver alertness.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Performance Analysis of Keypoints Detection and Description Algorithms for Stereo Vision Based Odometry.

Sensors (Basel, Switzerland)·2025
Same author

Using Gesture Recognition for AGV Control: Preliminary Research.

Sensors (Basel, Switzerland)·2023
Same author

Moisture Determination for Fine-Sized Copper Ore by Computer Vision and Thermovision Methods.

Sensors (Basel, Switzerland)·2023
Same author

Measurement-Based Modelling of Material Moisture and Particle Classification for Control of Copper Ore Dry Grinding Process.

Sensors (Basel, Switzerland)·2021
Same author

Chladni Figures in Modal Analysis of a Double-Panel Structure.

Sensors (Basel, Switzerland)·2020

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Human-Computer Interaction

Background:

  • Driver fatigue detection is crucial for road safety.
  • Existing methods using Eye Aspect Ratio (EAR) and Percentage of Eye Closure (PERCLOS) suffer from false positives due to normal facial activities.
  • Ambiguity in facial signals and geometric indicators necessitates a more robust approach.

Purpose of the Study:

  • To develop a context-aware framework for robust driver fatigue assessment.
  • To integrate behavioral, geometric, and emotional information for improved accuracy.
  • To provide an interpretable estimation of driver state beyond binary classification.

Main Methods:

  • Utilized MediaPipe Face Mesh for facial landmark extraction.
  • Implemented adaptive eye-closure detection with multi-stage validation (EAR, mouth activity, head pose).
Keywords:
behavioural analysisemotion-aware modellingfatigue risk assessmentfatigued driver detectionmultimodal analysis

Related Experiment Videos

Last Updated: Jul 16, 2026

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research
07:15

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Published on: December 18, 2020

  • Employed EfficientNet-B0 for emotion recognition and aggregated emotional variability and relevance over time.
  • Fused behavioral data (blinking, yawning, head nodding) with emotional context for a multi-level fatigue model.

    • Main Results:

    • Achieved 94% accuracy in driver fatigue detection on the NTHU-DDD dataset.
    • Demonstrated improved robustness against non-frontal head poses and expressive facial behaviors.
    • The Driver Fatigue Risk Index provides an interpretable, non-binary estimation of driver state.

    Conclusions:

    • The proposed context-aware framework significantly enhances the robustness and accuracy of vision-based driver fatigue detection.
    • Integrating emotional and behavioral context with geometric features overcomes limitations of traditional methods.
    • This approach offers a more reliable and interpretable solution for monitoring driver alertness and improving road safety.