Human activity recognition and prediction systems are crucial to the safety of autonomous vehicles. Specifically, a challenge that has been the subject of much research is the ability to differentiate between adult and child pedestrians. Failure to correctly identify the type of pedestrian can cause accidents. In this paper, we propose a novel multiple object tracking system for autonomous vehicles that is designed to overcome the challenges associated with differentiating between adult and child pedestrians. Our system uses modern machine learning based object detection and tracking methods to identify the type of pedestrian and measure various characteristics about their behavior, such as their speed and trajectory. Results from experiments to evaluate the effectiveness of our proposed framework show that our system is able to correctly differentiate between adult and child pedestrians and can provide useful information about their movements to the autonomous vehicle. Overall, our research demonstrates the potential of our multiple object tracking system to improve the safety and performance of autonomous vehicles.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Machine Learning Based Pedestrian Detection and Tracking for Autonomous Vehicles


    Contributors:


    Publication date :

    2023-03-08


    Size :

    418901 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Pedestrian Tracking and Stereo Matching of Tracklets for Autonomous Vehicles

    Xue, Hao / Huynh, Du Q. / Reynolds, Mark | IEEE | 2019


    Locked pedestrian detection and prediction for autonomous vehicles

    ZHU FAN | European Patent Office | 2023

    Free access

    LOCKED PEDESTRIAN DETECTION AND PREDICTION FOR AUTONOMOUS VEHICLES

    ZHU FAN | European Patent Office | 2021

    Free access

    Optimized deep learning for pedestrian safety in autonomous vehicles

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

    Free access