DETEKSI PELANGGARAN MELAWAN ARUS LALU LINTAS MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE PADA VIDEO LALU LINTAS DI JALAN KOTA PALEMBANG

NUGROHO, MUHAMMAD ADI and Oklilas, Ahmad Fali (2025) DETEKSI PELANGGARAN MELAWAN ARUS LALU LINTAS MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE PADA VIDEO LALU LINTAS DI JALAN KOTA PALEMBANG. Undergraduate thesis, Sriwijaya University.

	Image RAMA_56201_09011282025066_Cover.jpeg - Cover Image Available under License Creative Commons Public Domain Dedication. Download (383kB)
	Text RAMA_56201_09011282025066.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
	Text RAMA_56201_09011282025066_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7MB) | Request a copy
	Text RAMA_56201_09011282025066_0015107201_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_56201_09011282025066_0015107201_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (486kB) | Request a copy
	Text RAMA_56201_09011282025066_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_09011282025066_0015107201_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (938kB) | Request a copy
	Text RAMA_56201_09011282025066_0015107201_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (227kB) | Request a copy
	Text RAMA_56201_09011282025066_0015107201_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (246kB) | Request a copy
	Text RAMA_56201_09011282025066_0015107201_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy

Abstract

This research aims to develop an anti-traffic violation detection system by utilizing a combination of YOLOV8 algorithm used to detect vehicles from traffic video footage and SVM used to classify the violation level into three categories: low, medium, and high. The dataset used consists of 7,412 vehicle images for the YOLO model. For SVM, a reference table of 160 rows will be provided as training data and 100 video recordings of violations will be processed where 70% will be the test data and 30% will be the validation data. The training results of the YOLOv8 model show an accuracy of 88.76% for training data, 88.67% for validation, and 86% for testing. Meanwhile, the SVM model produces 93% accuracy on validation data (30 samples) and 86% on testing data (70 samples). Based on the classification results, as many as 66% of violations in Palembang City are classified into the low category, with the most violations committed by motorcyclists.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Pelanggaran Lalu Lintas, Lawan Arus Lalu Lintas, Kota Palembang, YOLOv8, Deteksi Objek, Kendaraan, Support Vector Machine (SVM), Klasifikasi, Tingkat Pelanggaran.
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Muhammad Adi Nugroho
Date Deposited:	23 Jul 2025 02:46
Last Modified:	23 Jul 2025 02:46
URI:	http://repository.unsri.ac.id/id/eprint/180020

Actions (login required)

View Item