Due to distortion, limitations of vision, and occlusion, most of the existing vacant parking slot detection methods with a standalone around view monitor (AVM) are prone to miss some parking slots and incorrectly identify whether the parking slot is vacant. To overcome this problem, we propose a complete method for vacant parking slot detection and tracking during driving and parking. Considering the different conditions of driving and parking, two different deep convolutional neural networks (DCNNs) are used to detect parking slots, of which the vacant parking slot detection network (VPS-Net) is used to detect vacant parking slots during driving, and the directional marking point detection network (DMPR-PS) is used to detect the directional marking points of the target parking slot during parking. Furthermore, in the driving process, we design a new matching rule and tracking management rule based on the Kernelized Correlation Filter (KCF) to track the parking slots, and fuse classification results of multiple frames to determine the occupancy status. In the parking process, since the parking slot is easily blocked by the vehicle, we design another new tracker to track the directional marking points and infer the complete parking slot using tracking results and prior geometric information. To evaluate the proposed method, a labeled video sequence dataset is established. Experiments show that the proposed method has improved the accuracy and continuity of vacant parking slots detection and positioning whether in the driving process or parking process.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Vacant parking slot detection and tracking during driving and parking with a standalone around view monitor


    Beteiligte:
    Li, Wei (Autor:in) / Cao, Libo (Autor:in) / Yan, Lingbo (Autor:in) / Liao, Jiacai (Autor:in) / Wang, Zhen (Autor:in)


    Erscheinungsdatum :

    2021-05-01


    Format / Umfang :

    13 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch







    VACANT PARKING SPACE DETECTION APPARATUS AND VACANT PARKING SPACE DETECTION METHOD

    HIRAI YOSHITO | Europäisches Patentamt | 2020

    Freier Zugriff

    Vacant parking space detection apparatus and vacant parking space detection method

    HIRAI YOSHITO | Europäisches Patentamt | 2020

    Freier Zugriff