The proliferation of autonomous vehicles (AVs) research and technologies have the potential of advancing intelligent transportation systems to new horizons. One of the main issues that relate to the AV operation is the need to enable these vehicles to comprehend the behavior of road users the same way as human drives would normally do. For this purpose, significant research efforts have focused on the issue of enabling the AVs to predict the intention of pedestrians especially as relates to road-crossing. This is done by interpreting some attributes of the pedestrians' behaviors as they approach the areas where they can potentially attempt to cross the street. In this study, we introduce a novel architecture of a pedestrian intention prediction model. This architecture includes the processing of the collected data in two parallel paths. In these two paths, image and non-image data are processed via two types of transformer-based models and then fused into an intention prediction classifier. Experimental simulations show that the proposed technique produces significantly better pedestrians' intention prediction results, as compared to leading models from the literature.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    An Optimized Hybrid Transformer-Based Technique for Real-Time Pedestrian Intention Estimation in Autonomous Vehicles


    Contributors:


    Publication date :

    2023-10-16


    Size :

    1359531 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Autonomous Driving: Framework for Pedestrian Intention Estimation in a Real World Scenario

    Alvarez, Walter Morales / Moreno, Francisco Miguel / Sipele, Oscar et al. | IEEE | 2020


    AUTONOMOUS DRIVING: FRAMEWORK FOR PEDESTRIAN INTENTION ESTIMATION IN A REAL WORLD SCENARIO

    Morales-Alvarez, Walter / Moreno, Francisco Miguel / Sipele, Oscar et al. | British Library Conference Proceedings | 2020


    Optimized deep learning for pedestrian safety in autonomous vehicles

    Farhat, Wajdi / Rhaiem, Olfa Ben / Faiedh, Hassene et al. | Elsevier | 2025

    Free access


    Autonomous Driving: Framework for Pedestrian Intention Estimationin a Real World Scenario

    Alvarez, Walter Morales / Moreno, Francisco Miguel / Sipele, Oscar et al. | ArXiv | 2020

    Free access