This paper presents a novel approach for pedestrian detection in nighttime with a normal camera. Generally, there is a real-time requirement in the pedestrian detection system which limits the computational complexity of algorithms. Thus most systems utilize the thresholding method for pedestrian detection or segmentation. However, the single adaptive threshold based approach doesn't always work well and sometimes gives poor results. In this paper, we propose adaptive hysteresis based segmentation algorithm which holds two adaptive thresholds. This inspiration comes from the Canny operator which uses hysteresis for edge thresholding. Furthermore, we expand the hysteresis to be proper for region segmentation in pedestrian detection. Experiments prove that the proposed method performs well most of the time and improves the ability of the pedestrian detection system.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Adaptive hysteresis thresholding based pedestrian detection in nighttime using a normal camera


    Beteiligte:
    Junfeng Ge, (Autor:in) / Yupin Luo, (Autor:in) / Deyun Xiao, (Autor:in)


    Erscheinungsdatum :

    2005-01-01


    Format / Umfang :

    4159583 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Near-Infrared-Based Nighttime Pedestrian Detection Using Grouped Part Models

    Lee, Yi-Shu / Chan, Yi-Ming / Fu, Li-Chen et al. | IEEE | 2015



    Camera Based Pedestrian Detection

    Schiele, Bernt / Wojek, Christian | Springer Verlag | 2015


    Evaluation of Nighttime Pedestrian Recognition Assistance System

    Hashimoto, H. / Takatsudo, I. / Tsuji, T. et al. | British Library Conference Proceedings | 2005