Traditional vision based vehicle detection methods are more successful in detecting front and rear vehicles. However, the problem of detecting vehicles under various poses still presents a great deal of difficulty. Pose variation leads to limit the use of vision based driver assistance systems. In this paper, we present a Conditional Random Fields (CRFs) based algorithm that can detect vehicles under various poses. We treat this problem in a different way. We extract textural properties from small image patches as well as colors. Then CRFs model is employed to incorporate the contextual information. Firstly, we classify these patches into vehicular surfaces or background surfaces. Then we use clustering algorithm to eliminate the false alarms and detect multiple vehicles. From the quantitative evaluation of the proposed methods, our algorithm can be used in many practical applications that do not need accurate segmentation of vehicles.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Vehicle detection under varying poses using Conditional Random Fields


    Beteiligte:
    Xuetao Zhang, (Autor:in) / Nanning Zheng, (Autor:in)


    Erscheinungsdatum :

    01.09.2010


    Format / Umfang :

    1038610 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Car Detection Using Multi-Feature Selection for Varying Poses

    Son, T.T. / Mita, S. | British Library Conference Proceedings | 2009


    Car detection using multi-feature selection for varying poses

    Son, Tran Thai / Mita, Seiichi | IEEE | 2009


    Curb reconstruction using Conditional Random Fields

    Siegemund, J / Pfeiffer, D / Franke, U et al. | IEEE | 2010


    Visual vehicle tracking based on conditional random fields

    Yuqiang Liu / Kunfeng Wang / Fei-Yue Wang | IEEE | 2014


    Multi-lane detection in urban driving environments using conditional random fields

    Hur, Junhwa / Kang, Seung-Nam / Seo, Seung-Woo | IEEE | 2013