Driver cognitive distraction detection: Feature estimation and implementation

Matti Kutila, Maria Jokela, Tapani Mäkinen, Jouko Viitanen, Gustav Markkula, Trent Victor

    Research output: Contribution to journalArticleScientificpeer-review

    23 Citations (Scopus)

    Abstract

    Driver assistance systems and electronics (e.g. navigators, cell phones, etc.) steal increasing amounts of driver attention. Therefore, the vehicle industry is striving to build a driving environment where input–output devices are smartly scheduled, allowing sufficient time for the driver to focus attention on the surrounding traffic. To enable a smart human–machine interface (HMI), the driver’s momentary state needs to be measured. This paper describes a facility for monitoring the distraction of a driver and presents some early evaluation results. The module is able to detect the driver’s visual and cognitive workload by fusing stereo vision and lane tracking data, running both rule–based and support-vector machine (SVM) classification methods. The module has been tested with data from a truck and a passenger car. The results show over 80% success in detecting visual distraction and a 68–86 % success in detecting cognitive distraction, which are satisfactory results.
    Original languageEnglish
    Pages (from-to)1027-1040
    JournalProceedings of the Institution of Mechanical Engineers Part D: Journal of Automobile Engineering
    Volume221
    Issue number9
    DOIs
    Publication statusPublished - 2007
    MoE publication typeA1 Journal article-refereed

    Fingerprint

    Stereo vision
    Passenger cars
    Trucks
    Support vector machines
    Electronic equipment
    Monitoring
    Industry

    Keywords

    • Cognitive distraction
    • vehicle
    • machine vision
    • driver monitoring
    • SVM

    Cite this

    @article{dda73ed709e54cf7b853db9b159fce80,
    title = "Driver cognitive distraction detection: Feature estimation and implementation",
    abstract = "Driver assistance systems and electronics (e.g. navigators, cell phones, etc.) steal increasing amounts of driver attention. Therefore, the vehicle industry is striving to build a driving environment where input–output devices are smartly scheduled, allowing sufficient time for the driver to focus attention on the surrounding traffic. To enable a smart human–machine interface (HMI), the driver’s momentary state needs to be measured. This paper describes a facility for monitoring the distraction of a driver and presents some early evaluation results. The module is able to detect the driver’s visual and cognitive workload by fusing stereo vision and lane tracking data, running both rule–based and support-vector machine (SVM) classification methods. The module has been tested with data from a truck and a passenger car. The results show over 80{\%} success in detecting visual distraction and a 68–86 {\%} success in detecting cognitive distraction, which are satisfactory results.",
    keywords = "Cognitive distraction, vehicle, machine vision, driver monitoring, SVM",
    author = "Matti Kutila and Maria Jokela and Tapani M{\"a}kinen and Jouko Viitanen and Gustav Markkula and Trent Victor",
    note = "HUO: Projektin nimi: AIDE - Adaptive Integrated Driver-vehicle InterfacE Project code: 612",
    year = "2007",
    doi = "10.1243/09544070JAUTO332",
    language = "English",
    volume = "221",
    pages = "1027--1040",
    journal = "Proceedings of the Institution of Mechanical Engineers Part D: Journal of Automobile Engineering",
    issn = "0954-4070",
    publisher = "SAGE Publications",
    number = "9",

    }

    Driver cognitive distraction detection : Feature estimation and implementation. / Kutila, Matti; Jokela, Maria; Mäkinen, Tapani; Viitanen, Jouko; Markkula, Gustav; Victor, Trent.

    In: Proceedings of the Institution of Mechanical Engineers Part D: Journal of Automobile Engineering, Vol. 221, No. 9, 2007, p. 1027-1040.

    Research output: Contribution to journalArticleScientificpeer-review

    TY - JOUR

    T1 - Driver cognitive distraction detection

    T2 - Feature estimation and implementation

    AU - Kutila, Matti

    AU - Jokela, Maria

    AU - Mäkinen, Tapani

    AU - Viitanen, Jouko

    AU - Markkula, Gustav

    AU - Victor, Trent

    N1 - HUO: Projektin nimi: AIDE - Adaptive Integrated Driver-vehicle InterfacE Project code: 612

    PY - 2007

    Y1 - 2007

    N2 - Driver assistance systems and electronics (e.g. navigators, cell phones, etc.) steal increasing amounts of driver attention. Therefore, the vehicle industry is striving to build a driving environment where input–output devices are smartly scheduled, allowing sufficient time for the driver to focus attention on the surrounding traffic. To enable a smart human–machine interface (HMI), the driver’s momentary state needs to be measured. This paper describes a facility for monitoring the distraction of a driver and presents some early evaluation results. The module is able to detect the driver’s visual and cognitive workload by fusing stereo vision and lane tracking data, running both rule–based and support-vector machine (SVM) classification methods. The module has been tested with data from a truck and a passenger car. The results show over 80% success in detecting visual distraction and a 68–86 % success in detecting cognitive distraction, which are satisfactory results.

    AB - Driver assistance systems and electronics (e.g. navigators, cell phones, etc.) steal increasing amounts of driver attention. Therefore, the vehicle industry is striving to build a driving environment where input–output devices are smartly scheduled, allowing sufficient time for the driver to focus attention on the surrounding traffic. To enable a smart human–machine interface (HMI), the driver’s momentary state needs to be measured. This paper describes a facility for monitoring the distraction of a driver and presents some early evaluation results. The module is able to detect the driver’s visual and cognitive workload by fusing stereo vision and lane tracking data, running both rule–based and support-vector machine (SVM) classification methods. The module has been tested with data from a truck and a passenger car. The results show over 80% success in detecting visual distraction and a 68–86 % success in detecting cognitive distraction, which are satisfactory results.

    KW - Cognitive distraction

    KW - vehicle

    KW - machine vision

    KW - driver monitoring

    KW - SVM

    U2 - 10.1243/09544070JAUTO332

    DO - 10.1243/09544070JAUTO332

    M3 - Article

    VL - 221

    SP - 1027

    EP - 1040

    JO - Proceedings of the Institution of Mechanical Engineers Part D: Journal of Automobile Engineering

    JF - Proceedings of the Institution of Mechanical Engineers Part D: Journal of Automobile Engineering

    SN - 0954-4070

    IS - 9

    ER -