• Login
    View Item 
    •   USU-IR Home
    • Faculty of Computer Science and Information Technology
    • Department of Information Technology
    • Undergraduate Theses
    • View Item
    •   USU-IR Home
    • Faculty of Computer Science and Information Technology
    • Department of Information Technology
    • Undergraduate Theses
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Deteksi Keberadaan Manusia untuk Mengontrol Pengguna Televisi dengan YOLOv5 secara Real Time Menggunakan Rock Pi

    Detection of Human Presence for Control Television Users with YOLOv5 in Real Time Using Rock Pi

    Thumbnail
    View/Open
    Cover (221.1Kb)
    Fulltext (1.398Mb)
    Date
    2024
    Author
    Lubis, Alya Febriani
    Advisor(s)
    Hizriadi, Ainul
    Purnamawati, Sarah
    Metadata
    Show full item record
    Abstract
    The use of electronic devices is increasingly used by the community today, including television. Television functions as entertainment. However, there are some people who only turn on the television but no one is in the room or didn’t use the television according to its function, causing the television to heat up quickly and easily damaged. In addition, there are times when television users, especially children, watch television too close to the screen, causing eye fatigue and damage. Therefore, to overcome these problems, a system that controls the television in realtime is needed. In this study, human detection will be carried out with the category of adults and children using the You Only Look Once (YOLO) version 5 method which will be integrated with the Rock Pi device. This Rock Pi device is used to control the relay. The relay will disable the television if the system cannot find people. Rock Pi will also control the buzzer. The buzzer will provide a warning if there are people who have been detected too close to the screen, because the distance from the object to the television screen will also be measured on the system. This human detection system to control the use of television in this study has been carried out and runs well with an accuracy of 83,24%, with precision reach 0,87 and recall 0,83.
    URI
    https://repositori.usu.ac.id/handle/123456789/95954
    Collections
    • Undergraduate Theses [866]

    Repositori Institusi Universitas Sumatera Utara - 2025

    Universitas Sumatera Utara

    Perpustakaan

    Resource Guide

    Katalog Perpustakaan

    Journal Elektronik Berlangganan

    Buku Elektronik Berlangganan

    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV
     

     

    Browse

    All of USU-IRCommunities & CollectionsBy Issue DateTitlesAuthorsAdvisorsKeywordsTypesBy Submit DateThis CollectionBy Issue DateTitlesAuthorsAdvisorsKeywordsTypesBy Submit Date

    My Account

    LoginRegister

    Repositori Institusi Universitas Sumatera Utara - 2025

    Universitas Sumatera Utara

    Perpustakaan

    Resource Guide

    Katalog Perpustakaan

    Journal Elektronik Berlangganan

    Buku Elektronik Berlangganan

    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV