The increase in the volume of vehicles utilizing our roads has highlighted the seriousness of the ongoing problem of traffic congestion. This problem is even worse at intersections, where a line of cars waits patiently for their turn to move forward. The traditional traffic light systems, which were originally intended to handle a less intense traffic load, are now having difficulty keeping up with the increasing number of vehicles, which further complicates the situation. We have adopted cutting-edge technologies, particularly those found in the fields of computer vision and machine learning, to tackle this modern dilemma. Our methodology is based on the application of a state-of-the-art system powered by a deep Convolutional Neural Network, which we call You Only Look Once (YOLO). With the help of this cutting-edge technology, we can quickly and thoroughly examine real-time data at signalized road crossings to gain a sophisticated understanding of the constantly changing traffic environment. Once we have a thorough understanding of the complex traffic dynamics thanks to YOLO's capabilities, we use this knowledge to make the most out of traffic light phases. We focus on closely examining important data elements, like the average wait time for a car and the number of cars in the line. The main goal is to create a coordinated and efficient traffic flow. This reduces the amount of time that drivers must wait in traffic overall and gives priority to safe and effective vehicle movement through intersections, resulting in a more responsive and fluid urban mobility experience.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Optimization of Vehicular Congestion Control in Traffic Signals using YOLO algorithm


    Beteiligte:
    Sivaganesan, D. (Autor:in) / Kumar, S. Barath (Autor:in) / Krishnadharani, S. (Autor:in) / Rashmitha, G. (Autor:in)


    Erscheinungsdatum :

    28.06.2024


    Format / Umfang :

    473102 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Traffic Congestion Prediction Using Categorized Vehicular Speed Data

    Kumar, Manoj / Kumar, Kranti | Springer Verlag | 2022


    Intelligent Traffic Control System Using YOLO Algorithm for Traffic Congested Cities

    Mou, Afsana Rahman / Milanova, Mariofanna / Piya, Sumaiya Sharmin | IEEE | 2023


    New pedestrian-vehicular traffic control signals

    Engineering Index Backfile | 1934


    Machine Learning Solutions to Vehicular Traffic Congestion

    Chhatpar, Pavan / Doolani, Nimesh / Shahani, Sumeet et al. | IEEE | 2018