Anticipating human actions in front of autonomous vehicles is a challenging task. Several papers have recently proposed model architectures to address this problem by combining multiple input features to predict pedestrian crossing actions. This paper focuses specifically on using images of the pedestrian's context as an input feature. We present several spatio-temporal model architectures that utilize standard CNN and Transformer modules to serve as a backbone for pedestrian anticipation. However, the objective of this paper is not to surpass state-of-the-art benchmarks but rather to analyze the positive and negative predictions of these models. Therefore, we provide insights on the explainability of vision-based Transformer models in the context of pedestrian action prediction. We will highlight cases where the model can achieve correct quantitative results but falls short in providing human-like explanations qualitatively, emphasizing the importance of investing in explainability for pedestrian action anticipation problems.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Analysis Over Vision-Based Models for Pedestrian Action Anticipation


    Beteiligte:
    Achaji, Lina (Autor:in) / Moreau, Julien (Autor:in) / Aioun, Francois (Autor:in) / Charpillet, Francois (Autor:in)


    Erscheinungsdatum :

    2023-09-24


    Format / Umfang :

    2994541 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Anticipation in a velocity-based model for pedestrian dynamics

    Xu, Qiancheng / Chraibi, Mohcine / Seyfried, Armin | Elsevier | 2021


    DPCIAN: A Novel Dual-Channel Pedestrian Crossing Intention Anticipation Network

    Yang, Biao / Wei, Zhiwen / Hu, Hongyu et al. | IEEE | 2024


    PEDESTRIAN ACTION PREDICTION DEVICE AND PEDESTRIAN ACTION PREDICTION METHOD

    KINDO TOSHIKI / OGAWA MASAHIRO / FUNAYAMA RYUJI | Europäisches Patentamt | 2018

    Freier Zugriff

    Infrared stereo vision-based pedestrian detection

    Bertozzi, M. / Broggi, A. / Lasagni, A. et al. | IEEE | 2005


    Infrared Stereo Vision-based Pedestrian Detection

    Bertozzi, M. / Broggi, A. / Lasagni, A. et al. | British Library Conference Proceedings | 2005