The human driver is no longer the only one concerned with the complexity of the driving scenarios. Autonomous vehicles (AV) are similarly becoming involved in the process. Nowadays, the development of AV in urban places raises essential safety concerns for vulnerable road users (VRUs) such as pedestrians. Therefore, to make the roads safer, it is critical to classify and predict the pedestrians’ future behavior. In this paper, we present a framework based on multiple variations of the Transformer models able to predict the pedestrian street-crossing decision-making based on the dynamics of its initiated trajectory. We showed that using solely bounding boxes as input features can outperform the previous state-of-the-art results by reaching a prediction accuracy of 91% and an F1-score of 0.83 on the PIE dataset. In addition, we introduced a large-size simulated dataset (CP2A) using CARLA for action prediction. Our model has similarly reached high accuracy (91%) and F1-score (0.91) on this dataset. Interestingly, we showed that pre-training our Transformer model on the CP2A dataset and then fine-tuning it on the PIE dataset is beneficial for the action prediction task. Finally, our model’s results are successfully supported by the “human attention to bounding boxes” experiment which we created to test humans’ ability for pedestrian action prediction without the need for environmental context. The code for the dataset and the models is available at: https://github.com/ linaashaji/Action_Anticipation


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Is attention to bounding boxes all you need for pedestrian action prediction?


    Beteiligte:


    Erscheinungsdatum :

    05.06.2022


    Format / Umfang :

    3163555 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Pedestrian 3D Bounding Box Prediction

    Saadatnejad, Saeed / Ju, Yi Zhou / Alahi, Alexandre | TIBKAT | 2022

    Freier Zugriff

    Stability analysis of kinetic oriented bounding boxes

    Meulemans, Wouter / Verbeek, Kevin / Wulms, Jules | BASE | 2019

    Freier Zugriff

    PEDESTRIAN ACTION PREDICTION DEVICE AND PEDESTRIAN ACTION PREDICTION METHOD

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

    Freier Zugriff

    Methods and systems for object tracking using bounding boxes

    GAO PETER | Europäisches Patentamt | 2019

    Freier Zugriff