In this work, we propose a framework for the recognition and prediction of driver maneuvers by considering holistic cues. With an array of sensors, driver's head, hand, and foot gestures are being captured in a synchronized manner together with lane, surrounding agents, and vehicle parameters. An emphasis is put on real-time algorithms. The cues are processed and fused using a latent-dynamic discriminative framework. As a case study, driver activity recognition and prediction in overtaking situations is performed using a naturalistic, on-road dataset. A consequence of this work would be in development of more effective driver analysis and assistance systems.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Predicting driver maneuvers by learning holistic features


    Contributors:


    Publication date :

    2014-06-01


    Size :

    1916667 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    PREDICTING DRIVER MANEUVERS BY LEARNING HOLISTIC FEATURES

    Ohn-Bar, E. / Tawari, A. / Martin, S. et al. | British Library Conference Proceedings | 2014


    Modeling Driver Behavior during Merge Maneuvers

    C. C. Kou / R. B. Machemehl | NTIS | 1997


    Driver-Model of Lane Change Maneuvers

    Ehmanns, D. / ITS Congress Association | British Library Conference Proceedings | 2000


    Measuring Driver Performance in Braking Maneuvers

    Koppa, Rodger J. | Online Contents | 1996


    Measuring Driver Performance in Braking Maneuvers

    Koppa, Rodger J. / Fambro, Daniel B. / Zimmer, Richard A. | Transportation Research Record | 1996