IDENTIFIKASI KENDARAAN DENGAN MENGGUNAKAN YOLO DAN UNTUK MENENTUKAN KEPADATAN KENDARAAN DI JALAN PROTOKOL KOTA PALEMBANG MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK (CNN)

ALMUNDZIR, KHALILURRAHMAN and Oklilas, Ahmad Fali (2023) IDENTIFIKASI KENDARAAN DENGAN MENGGUNAKAN YOLO DAN UNTUK MENENTUKAN KEPADATAN KENDARAAN DI JALAN PROTOKOL KOTA PALEMBANG MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK (CNN). Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011281924051.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_56201_09011281924051_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_56201_09011281924051_0015107201_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_56201_09011281924051_0015107201_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (363kB) | Request a copy
	Text RAMA_56201_09011281924051_0015107201_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011281924051_0015107201_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011281924051_0015107201_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (42kB) | Request a copy
	Text RAMA_56201_09011281924051_0015107201_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (102kB) | Request a copy
	Text RAMA_56201_09011281924051_0015107201_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy

Abstract

The increasing volume of vehicles each year results in an escalating daily traffic volume, leading to issues such as congestion and vehicle density that adversely affect various sectors. Therefore, this research aims to develop a vehicle detection system and vehicle count using the You Only Look Once (YOLO) generation 8 algorithm, assisted by the DeepSort architecture, to count the number of vehicles crossing a Counter line. In addition to object detection, this research study also focuses on using Convolutional Neural Network (CNN) methods to determine road conditions, whether they are considered smooth, moderate, or congested. To support this research study, a dataset consisting of 3592 image files and 72 video files containing information about vehicles such as motorcycles and cars was used. However, for the dataset model used in this research study, there are five variables: motorcycles, cars, red lights, green lights, and zebra crossings. From the image dataset, a YOLOv8 model was obtained with a training accuracy of 93.73% and a testing accuracy of 93.73%. The accuracy of the YOLOv8 model already demonstrates excellent performance in detecting vehicle objects. During the creation of the CNN model, an accuracy of 94.27% was achieved, and when testing the output video results in the form of a CSV file, it can be concluded that Monday mornings tend to be congested, Wednesdays are relatively smooth, Fridays have moderate road conditions on average, and Saturdays also have moderate conditions on average. Interestingly, on Mondays, Wednesdays, Fridays, or Saturdays, in the afternoon, the road conditions in Palembang city are always moderate.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Kepadatan kendaraan, You Only Look Once (YOLO), Convolutional Neural Network (CNN), DeepSort
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics > Q325.5 Machine learning Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Khalilurrahman Almundzir
Date Deposited:	11 Jan 2024 05:32
Last Modified:	11 Jan 2024 05:32
URI:	http://repository.unsri.ac.id/id/eprint/137898

Actions (login required)

View Item