In this paper, we propose a novel deep learning architecture for the end-to-end classification of unsafe maneuvers from dashcam data; the proposed model is based on an innovative two-stream architecture capable of processing both video and GPS/IMU signals as input streams. A wide experimentation on a well known naturalistic driving dataset (SHRP2 NDS) shows that the two sources of information complement each other in the classification task and proves the effectiveness of the proposed approach. As a by-product of this research, we propose and make available a novel classification of safety-critical events based on the unsafe maneuver leading to them, which is representative of the real distribution of car crashes and near crashes.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Two-stream neural architecture for unsafe maneuvers classification from dashcam videos and GPS/IMU sensors


    Beteiligte:


    Erscheinungsdatum :

    20.09.2020


    Format / Umfang :

    459135 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Unsafe Maneuver Classification From Dashcam Video and GPS/IMU Sensors Using Spatio-Temporal Attention Selector

    Simoncini, Matteo / de Andrade, Douglas Coimbra / Taccari, Leonardo et al. | IEEE | 2022


    Classifying Ego-Vehicle Road Maneuvers from Dashcam Video

    Zekany, Stephen A. / Dreslinski, Ronald G. / Wenisch, Thomas F. | IEEE | 2019


    Towards Anomaly Detection in Dashcam Videos

    Haresh, Sanjay / Kumar, Sateesh / Zia, M. Zeeshan et al. | IEEE | 2020


    Classification of Crash and Near-Crash Events from Dashcam Videos and Telematics

    Taccari, Leonardo / Sambo, Francesco / Bravi, Luca et al. | IEEE | 2018


    Review of Accident Detection Methods Using Dashcam Videos for Autonomous Driving Vehicles

    Rocky, Arash / Wu, Qingming Jonathan / Zhang, Wandong | IEEE | 2024