Text detection in complex scene images is a challenging task for intelligent transportation. Recently, anchor mechanisms are widely utilized in scene text detection tasks. However, in existing methods, anchors are generally predefined empirically, degrading robustness to complex scenarios with various sizes and orientation variations. In this paper, we propose a novel Attention Anchor Mechanism (AAM), especially targeting at predicting appropriate anchors for each pixel. To be concrete, we regard a series of predefined anchors as basic anchors and utilize an attention model to predict weights corresponding to basic anchors. Consequently, the weighted sum of basic anchors in each pixel can obtain a predicted anchor. In this way, the gap between the predicted anchors and the corresponding ground truth boxes could be narrowed, making the network easier to regress. For facilitating the design of basic anchors, we adopt a dimension-decomposition mechanism to predict width, height, and angle of anchors, respectively. Extensive experiments on several public datasets demonstrate that our method achieves state-of-the-art performance.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Detecting Text in Scene and Traffic Guide Panels With Attention Anchor Mechanism


    Beteiligte:
    Hou, Jie-Bo (Autor:in) / Zhu, Xiaobin (Autor:in) / Liu, Chang (Autor:in) / Yang, Chun (Autor:in) / Wu, Long-Huang (Autor:in) / Wang, Hongfa (Autor:in) / Yin, Xu-Cheng (Autor:in)


    Erscheinungsdatum :

    01.11.2021


    Format / Umfang :

    5628414 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    ASAYAR: A Dataset for Arabic-Latin Scene Text Localization in Highway Traffic Panels

    Akallouch, Mohammed / Boujemaa, Kaoutar Sefrioui / Bouhoute, Afaf et al. | IEEE | 2022


    Text recognition on traffic panels from street-level imagery

    Gonzalez, A. / Bergasa, L. M. / Yebes, J. Javier et al. | IEEE | 2012


    Text Recognition on Traffic Panels from Street-Level Imagery

    Gonzalez, A. / Bergasa, L.M. / Yebes Torres, J.J. et al. | British Library Conference Proceedings | 2012


    Pretensioner with guide loop or anchor

    KUJAWA PETER P / STRNAD GEORGE J / GOHLKE MATT R et al. | Europäisches Patentamt | 2017

    Freier Zugriff

    PRETENSIONER WITH GUIDE LOOP OR ANCHOR

    KUJAWA PETER P / STRNAD GEORGE J / GOHLKE MATT R et al. | Europäisches Patentamt | 2016

    Freier Zugriff