We explore the problem of intersection classification using monocular on-board passive vision, with the goal of classifying traffic scenes with respect to road topology. We divide the existing approaches into two broad categories according to the type of input data: (a) first person vision (FPV) approaches, which use an egocentric view sequence as the intersection is passed; and (b) third person vision (TPV) approaches, which use a single view immediately before entering the intersection. The FPV and TPV approaches each have advantages and disadvantages. Therefore, we aim to combine them into a unified deep learning framework. Experimental results show that the proposed FPV-TPV scheme outperforms previous methods and only requires minimal FPV/TPV measurements.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Deep Intersection Classification Using First and Third Person Views


    Beteiligte:
    Koji, Takeda (Autor:in) / Kanji, Tanaka (Autor:in)


    Erscheinungsdatum :

    01.06.2019


    Format / Umfang :

    2801505 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    DEEP INTERSECTION CLASSIFICATION USING FIRST AND THIRD PERSON VIEWS

    Koji, Takeda / Kanji, Tanaka | British Library Conference Proceedings | 2019


    MACHINE LEARNING BASED HUMAN ACTIVITY DETECTION AND CLASSIFICATION IN FIRST AND THIRD PERSON VIDEOS

    BHATIA AMIT / WANG GUOQIANG / EL CHAMIE MAHMOUD et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    MACHINE LEARNING BASED HUMAN ACTIVITY DETECTION AND CLASSIFICATION IN FIRST AND THIRD PERSON VIDEOS

    BHATIA AMIT / WANG GOUQIANG / EL CHAMIE MAHMOUD et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    First Person and Third Person Perspective in Virtual Reality: Analysis of Cybersickness Symptoms

    Sri Sidhimantra, I Gde Agung / Herumurti, Darlis | BASE | 2021

    Freier Zugriff

    Ego-to-Exo: Interfacing Third Person Visuals from Egocentric Views in Real-time for Improved ROV Teleoperation

    Abdullah, Adnan / Chen, Ruo / Rekleitis, Ioannis et al. | ArXiv | 2024

    Freier Zugriff