Recent decades have seen an increase in the population density of cities, and today's megacities are densely inhabited locations with substantial land use encompassing residential, transit, sanitation and utilities as well as communication infrastructure. In the future, new types of road users will emerge as a consequence of new technology developments. As cities grow in population and highways become more congested, governmental agencies such as the Transportation Department and the National Highway Administration are under increasing pressure to improve their management services through the introduction of more efficient technology. In order to preserve life and establish long‐term, expense management methods, the objective is to forecast issues that have never previously been faced. Self‐driving vehicles will soon be legal in highly populated major cities where streets will be shared by pedestrians, bicycles, autos, and trucks, further complicating the situation. Adaptations to road and signal widths and timing will be required on a regular basis. Human involvement is still required to count and categorize turning vehicles and pedestrians at intersections, even with the use of traffic monitoring technology. Turning‐vehicle counts at traffic junctions may be resolved using our method, which is less invasive, requires no road excavating, and is less costly to implement. Cameras installed across cities, as well as any other camera, including those on mobile phones, may be used to capture video in real time or after they have been captured. Neural Networks and Deep Learning, as well as machine vision and a range of techniques and algorithms, are all used in our system to identify objects. An artificial convolutional neural network will be used to analyze moving objects in both still images and video recordings, allowing us to follow their motion and calculate their velocity as well as direction.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Traffic Management for Smart City Using Deep Learning


    Beteiligte:
    Rawat, Romil (Herausgeber:in) / Sowjanya, A. Mary (Herausgeber:in) / Patel, Syed Imran (Herausgeber:in) / Jaiswal, Varshali (Herausgeber:in) / Khan, Imran (Herausgeber:in) / Balaram, Allam (Herausgeber:in) / Gupta, Puja (Autor:in) / Singh, Upendra (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    2022-12-19


    Format / Umfang :

    11 pages




    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Smart Traffic Management System using Deep Learning for Smart City Applications

    Lingani, Guy M. / Rawat, Danda B. / Garuba, Moses | IEEE | 2019


    Smart traffic management system for smart city

    YE QINFA / TANG QING / ZHU WANRONG | Europäisches Patentamt | 2023

    Freier Zugriff

    Smart city traffic signal management system

    ZHANG FENG | Europäisches Patentamt | 2023

    Freier Zugriff

    SMART CITY TRAFFIC INFORMATION MANAGEMENT SYSTEM

    KIM MYUNG SUP | Europäisches Patentamt | 2023

    Freier Zugriff

    Smart control of traffic light using deep learning

    Kumar, Dr. M. Aravind / Sheela, P. | SLUB | 2023