This paper presents a novel system utilizing Un-manned Aerial Vehicles (UAVs) for real-time object detection and road safety monitoring. The proposed system leverages deep learning (DL) identify and classify object like potholes on congested Indian roads, particularly during late hours for enhanced accident prevention. A camera mounted on the drone captures images, which are then processed to detect and classify objects based on their characteristics and severity. The system employs Internet of Things (IoT) for data transmission and cloud storage for ubiquitous access and analysis. The results demonstrate the feasibility of the proposed system for intelligent road safety monitoring, offering timely alerts to authorities for prompt action. Whilst achieving an decent accuracy of 85 % for correct classification of potholes from the live-feed, the system works immaculately well in various conditions for detection.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Road Safety Monitoring using deep learning and Unmanned Aerial Vehicle




    Publication date :

    2024-03-01


    Size :

    1448378 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Real-time road monitoring unmanned aerial vehicle

    LIU CHUANCHU | European Patent Office | 2020

    Free access

    Unmanned Aerial Vehicle Surveying For Monitoring Road Construction Earthworks

    Julge, Kalev / Ellmann, Artu / Köök, Romet | BASE | 2019

    Free access

    UNMANNED AERIAL VEHICLE FOR MONITORING AND UNMANNED AERIAL VEHICLE MONITORING SYSTEM

    ABE TATSUYA / ASANO MASAHIRO | European Patent Office | 2023

    Free access

    Safety aerial photography unmanned aerial vehicle

    WU YI | European Patent Office | 2020

    Free access

    Unmanned aerial vehicle safety monitoring method and system

    ZENG JINGJING / LIN ZIYI / LI HONGBO | European Patent Office | 2024

    Free access