Gesture recognition is essential for the interaction of autonomous vehicles with humans. While the current approaches focus on combining several modalities like image features, keypoints and bone vectors, we present neural network architecture that delivers state-of-the-art results only with body skeleton input data. We propose the spatio-temporal multilayer perceptron for gesture recognition in the context of autonomous vehicles. Given 3D body poses over time, we define temporal and spatial mixing operations to extract features in both domains. Additionally, the importance of each time step is re-weighted with Squeeze-and-Excitation layers. An extensive evaluation of the TCG and Drive& Act datasets is provided to showcase the promising performance of our approach. Furthermore, we deploy our model to our autonomous vehicle to show its real-time capability and stable execution.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A Spatio-Temporal Multilayer Perceptron for Gesture Recognition


    Beteiligte:


    Erscheinungsdatum :

    05.06.2022


    Format / Umfang :

    1759513 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Modular, Multilayer Perceptron

    Cheng, Li-Jen / Liu, Tsuen-Hsi | NTRS | 1991


    Memristor crossbar based implementation of a multilayer perceptron

    Yakopcic, Chris / Taha, Tarek M. | IEEE | 2017


    GESTURE RECOGNITION DEVICE AND GESTURE RECOGNITION METHOD

    HIGUCHI DAIKI / OHASHI DAISUKE | Europäisches Patentamt | 2022

    Freier Zugriff

    Dynamic Texture Recognition by Spatio-Temporal Multiresolution Histograms

    Lu, Zongqing / Xie, Weixin / Pei, Jihong et al. | IEEE | 2005


    GESTURE RECOGNITION ASSISTANCE APPARATUS AND GESTURE RECOGNITION METHOD

    KIM JEONG / PARK JANG WOONG | Europäisches Patentamt | 2024

    Freier Zugriff