Deteksi Dan Identifikasi Rambu-Rambu Lalu Lintas Berbasis Citra Digital Menggunakan Metode YOLOV4

Salim, Ivan Ari Fadila (2022) Deteksi Dan Identifikasi Rambu-Rambu Lalu Lintas Berbasis Citra Digital Menggunakan Metode YOLOV4. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 06111740000063-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2024. Download (2MB) | Request a copy

Abstract

Ilmu pengetahuan dan teknologi saat ini mengalami perkembangan yang cukup pesat sehingga menyebabkan banyak sekali inovasi yang muncul demi memudahkan manusia untuk melakukan kegiatan sehari-harinya. Salah satu penerapan yang sedang dikembangkan dinamakan Intelligent Transportation System. Untuk mendukung hal tersebut kini di dunia otomotif sedang mencoba mengembangkan teknologi Advanced Driver Assistance Systems. Salah satu sistem didalamnya yang memiliki peranan penting ialah pendeteksian rambu-rambu lalu lintas. Pendeteksian rambu lalu lintas dapat menggunakan pengolahan citra digital dalam proses penarikan informasinya. Adapun data yang dibutuhkan untuk melakukan pendeteksian rambu-rambu lalu lintas dapat berupa video karena memungkinkan pendeteksian rambu-rambu secara terus menerus. Dengan berkembangnya proses pendeteksian objek, pada penelitian ini dilakukan pendeteksian rambu lalu lintas dengan basis video menggunakan metode You Only Look Once. Output yang dihasilkan dari penelitian tugas akhir ini menunjukan bahwa metode YOLOV4 yang diimplementasikan dalam bentuk program mampu menghasilkan pendeteksian rambu dengan tingkat akurasi sebesar 88,35% untuk kendaraan berkecepatan 20-30km/jam dan 80,56% untuk kendaraan dengan kecepatan 30-40km/jam.
================================================================================================
Science and technology is currently experiencing a fairly rapid development, causing a lot of innovations that appear to make it easier for humans to carry out their daily activities. One application that is being developed is called the Intelligent Transportation System. To support this, the automotive world is currently trying to develop Advanced Driver Assistance System technology. One of the systems in it that has an important role is the detection of traffic signs. Detection of traffic signs can use digital image processing in the process of retrieving the information. The data needed to detect traffict signs can be in form of video because it allows the detection of signs continuously. With the development of the object detection process, this research detect traffict signs on a video basis using the You Only Look Once method. The output of this final project is the YOLOV4 method which is implemented in the form of program capable of producing sign detection with a success rate of 88,35% for speed of vehicle is 20-30km/h and 80,56% for speed of vehicle is 30-40km/h

Item Type:	Thesis (Other)
Uncontrolled Keywords:	You Only Look Once, Rambu Lalu Lintas, Pengolahan Citra, Traffic Signs, Digital Image
Subjects:	Q Science > QA Mathematics > QA76.6 Computer programming. Q Science > QA Mathematics > QA76.76.A63 Application program interfaces R Medicine > R Medicine (General) > R858 Deep Learning T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques T Technology > TL Motor vehicles. Aeronautics. Astronautics > TL152.8 Vehicles, Remotely piloted. Autonomous vehicles.
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Mathematics > 44201-(S1) Undergraduate Thesis
Depositing User:	IVAN ARI FADILA SALIM
Date Deposited:	11 Feb 2022 02:49
Last Modified:	02 Nov 2022 02:01
URI:	http://repository.its.ac.id/id/eprint/93408

Actions (login required)

View Item