The high variability of sign appearance with partial occlusions in uncontrolled environments has made the detection of traffic signs a challenging problem in computer vision. In this study, an occlusion-robust traffic sign detection framework is proposed. To achieve occlusion-robust detection, a colour cubic feature called colour cubic local binary pattern (CC-LBP) is proposed to construct a coarse-to-fine cascaded detector. The CC-LBP utilises colour information and a self-adaptive threshold to express multiclass traffic signs, which can effectively remove non-object subwindows in the cascade-based detection. The verification experiments show that the proposed CC-LBP feature performs better than the previous rectangular features in representing multiclass traffic signs, and that the proposed occlusion-robust detection method can detect multiclass partial occluded traffic signs with high accuracy in real time.


    Zugriff

    Zugriff über TIB


    Exportieren, teilen und zitieren



    Titel :

    Occlusion-robust traffic sign detection via cascaded colour cubic feature


    Beteiligte:
    Liu, Chunsheng (Autor:in) / Chang, Faliang (Autor:in) / Liu, Chenyun (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    2016-06-01


    Format / Umfang :

    7 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Occlusion‐robust traffic sign detection via cascaded colour cubic feature

    Liu, Chunsheng / Chang, Faliang / Liu, Chenyun | Wiley | 2016

    Freier Zugriff

    Cascaded Segmentation-Detection Networks for Text-Based Traffic Sign Detection

    Zhu, Yingying / Liao, Minghui / Yang, Mingkun et al. | IEEE | 2018



    Traffic Sign Occlusion Detection Using Mobile Laser Scanning Point Clouds

    Huang, Pengdi / Cheng, Ming / Chen, Yiping et al. | IEEE | 2017


    Fast and robust traffic sign detection

    Soetedjo, A. / Yamada, K. | Tema Archiv | 2005