Motorbike is an interesting subject for both the object counting and object detecting problem. In developing countries, motorbike is the most popular vehicle. In traffic, knowledge of motorbike's count will reveal the overall density while knowing of motorbike's positions will reveal the direction of vehicles flows. For each of those tasks, we usually need a different approach. But, it will be wasteful if these approaches were to run separately. Therefore, we propose a combination of counting and detection which can reveal both the motorbike's count and position. To achieve this, our model reuses a result from the counting task, the density map, in the detection task. Using this density map will help us reduce the area for detection. The experiments show that our proposed method is faster than when the counting task and detection task were to run separately. It is also faster than the detection process running alone.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    An Unified Framework for Motorbike Counting and Detecting in Traffic Videos


    Beteiligte:
    Le, Thanh-Sach (Autor:in) / Huynh, Chi-Kien (Autor:in)


    Erscheinungsdatum :

    01.11.2015


    Format / Umfang :

    677132 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Motorbike power supply circuit, motorbike power supply system and motorbike

    LAI GUOGUI / YUAN ZHANGPING / CHEN ZHIYONG et al. | Europäisches Patentamt | 2015

    Freier Zugriff

    Robust image segmentation for overhead real time motorbike counting

    Dupuis, Y. / Subirats, P. / Vasseur, P. | IEEE | 2014


    MOTORBIKE TIRE

    OBANA KENTARO | Europäisches Patentamt | 2020

    Freier Zugriff

    Motorbike tire

    JUNICHIRO MOROZUMI | Europäisches Patentamt | 2015

    Freier Zugriff

    SAFE MOTORBIKE

    ACEVEDO ORDUÑA GERMAN LEONARDO | Europäisches Patentamt | 2023

    Freier Zugriff