In this paper, we propose a pilot hand detection method that combines the semi-supervised DenSe Learning (DSL) with a coordinate attention (CA) module, which we call CA-DSL. In our suggested approach, the CA module is added to Resnet, the backbone network of DSL. The CA module enhances the DSL’s capacity for learning and boosts the effectiveness of pilot hand detection. In addition, we establish a dataset for pilot hand detection that we call Pilot Hand (PH). On the PH dataset, we evaluate the suggested hand detection algorithm. and compared it with the state-of-the-art models. Experimental results show that the detection accuracy of CA-DSL outperforms the state-of-the-art models by 2%-7%.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Pilot Hand Detection Based on Semi-Supervised Learning


    Beteiligte:
    Qian, Ying (Autor:in) / Gu, Renshu (Autor:in) / Gu, Hongbin (Autor:in)


    Erscheinungsdatum :

    12.10.2022


    Format / Umfang :

    1975480 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch






    Driver Distraction Detection Using Semi-Supervised Machine Learning

    Liu, Tianchi / Yang, Yan / Huang, Guang-Bin et al. | IEEE | 2016


    Object Detection in Aerial Imagery Based on Enhanced Semi-Supervised Learning

    Yao, J. / Zhang, Z. / IEEE | British Library Conference Proceedings | 2005