About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
Innovations and Interdisciplinary Solutions for Underserved Areas. 6th EAI International Conference, InterSol 2023, Flic en Flac, Mauritius, September 16-17, 2023, Proceedings

Research Article

Distracker: An Intelligent Assistant for Real-Time Distracted Driving Detection and Mitigation

Cite
BibTeX Plain Text
  • @INPROCEEDINGS{10.1007/978-3-031-51849-2_3,
        author={Yash Krishna Sadien and Girish Bekaroo},
        title={Distracker: An Intelligent Assistant for Real-Time Distracted Driving Detection and Mitigation},
        proceedings={Innovations and Interdisciplinary Solutions for Underserved Areas. 6th EAI International Conference, InterSol 2023, Flic en Flac, Mauritius, September 16-17, 2023, Proceedings},
        proceedings_a={INTERSOL},
        year={2024},
        month={2},
        keywords={Distracker Distracted Driving Deep Learning Confusion Matrix In-Vehicle Intelligent Assistant},
        doi={10.1007/978-3-031-51849-2_3}
    }
    
  • Yash Krishna Sadien
    Girish Bekaroo
    Year: 2024
    Distracker: An Intelligent Assistant for Real-Time Distracted Driving Detection and Mitigation
    INTERSOL
    Springer
    DOI: 10.1007/978-3-031-51849-2_3
Yash Krishna Sadien, Girish Bekaroo,*
    *Contact email: g.bekaroo@mdx.ac.mu

    Abstract

    Distracted driving is a significant issue that has sparked extensive research in detection and mitigation methods, with previous studies exploring physiological sensors but finding them intrusive, leading to the rise of computer vision techniques, particularly deep learning, for non-intrusive and real-time detection. While recent research has demonstrated the accuracy of MobileNetV2-tiny in detecting distracted driving using the State Farm Distracted Driver Detection Dataset, there remains a need to address real-time mitigation strategies and cognitive distractions. To bridge these gaps, this study developed the ‘Distracker’ prototype, an intelligent agent using deep learning and eye-tracking algorithms to detect and mitigate manual, visual, and cognitive distractions in real-time, incorporating multi-modal alerts to enhance road safety. Through real-life driving experiments, participants engaged in various distracted driving tasks, and the Distracker prototype demonstrated a remarkable overall classification accuracy of 93.63%. These findings highlight the potential practical implementation of the Distracker prototype in vehicles, making significant strides in detecting and mitigating distracted driving and contributing to the larger goal of accident reduction and promoting secure driving experiences for all.

    Keywords
    Distracker Distracted Driving Deep Learning Confusion Matrix In-Vehicle Intelligent Assistant
    Published
    2024-02-02
    Appears in
    SpringerLink
    http://dx.doi.org/10.1007/978-3-031-51849-2_3
    Copyright © 2023–2025 ICST
    EBSCOProQuestDBLPDOAJPortico
    EAI Logo

    About EAI

    • Who We Are
    • Leadership
    • Research Areas
    • Partners
    • Media Center

    Community

    • Membership
    • Conference
    • Recognition
    • Sponsor Us

    Publish with EAI

    • Publishing
    • Journals
    • Proceedings
    • Books
    • EUDL