Traffic congestion is a significant problem in Sri Lanka, especially in urban areas. This research paper presents a traffic optimization system with emergency vehicle prioritization that utilizes deep learning to optimize the traffic flow at intersections. The system uses real-time traffic signal control based on traffic movement to optimize traffic flow at crossings. The study also provides a sophisticated emergency vehicle prioritizing system that uses deep learning to ensure faster and smoother transit for these vehicles, which is a major issue at junctions. Long wait times for emergency vehicles are a problem that the smart solution promises to solve, improving overall traffic management. The study addresses increasing traffic violations and accidents worldwide by concentrating on road safety. It provides a clever method that uses cutting-edge technologies to recognize and classify numerous breaches and mishaps. The method improves traffic operations and safety by rapidly notifying emergency services of occurrences. Traffic optimization reduces intersection waiting times and boosts emergency vehicle response by prioritizing them. Accident severity detection improves accident response time and lowers road violations via traffic violation detection, enhancing real-world impact.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Deep Learning-Based Approach for Real-Time Traffic Signal Optimization and Vehicle Surveillance




    Erscheinungsdatum :

    2023-12-07


    Format / Umfang :

    976984 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Robust Real-Time Traffic Surveillance with Deep Learning

    Jessica Fernández / José M. Cañas / Vanessa Fernández et al. | DOAJ | 2021

    Freier Zugriff


    - ON-DEVICE REAL-TIME TRAFFIC SIGNAL CONTROL SYSTEM BASED ON DEEP LEARNING

    TAEHA YU / KYUYOUNG SIM / SUKYOUNG CHO et al. | Europäisches Patentamt | 2022

    Freier Zugriff