IMPLEMENTING A FADED ROAD MARKING DETECTION SYSTEM USING THE WEB-BASED YOLOv8 METHOD

PRASETYO, DAMAR GALIH JATI (2026) IMPLEMENTING A FADED ROAD MARKING DETECTION SYSTEM USING THE WEB-BASED YOLOv8 METHOD. Tugas Akhir thesis, University of Technology Yogyakarta.

[img] Text
52204111375_Damar Galih Jati Prasetyo_ABSTRAK.pdf
Download (142kB)

Abstract

ABSTRACT Faded road markings pose a significant risk to traffic safety and flow by reducing driver visibility and potentially increasing the likelihood of accidents. This study aims to develop the FADETrack system to detect faded road markings using the YOLOv8 deep learning model. The dataset comprises 2,049 road marking images collected under various environmental conditions and labeled as either ‘Clear’ or ‘Faded.’ The dataset is split into training (70%), validation (20%), and testing (10%) subsets. Training was conducted using the basic YOLOv8n architecture with 50 epochs, an image size of 640 × 640 pixels, a batch size of 64, and a learning rate of 0.001. The research process includes acquiring road marking data, preprocessing images, detecting using the YOLOv8 model, and analyzing and visualizing the results. The system supports input from images, video streams, and real-time cameras. The application was developed in Python with a Flask-based backend and MySQL database. Test results demonstrated satisfactory performance, with a precision of 0.7193, recall of 0.7567, and mAP50 of 0.7479, indicating strong detection capability and potential as an efficient solution for road marking monitoring. This research is expected to continue evolving into a comprehensive and adaptive system for monitoring road marking conditions to enhance road safety. Keywords: Faded road markings, YOLOv8, deep learning, object detection, real-time.

Item Type: Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir)
Subjects: T Technology > T Technology (General) > T201 Patents. Trademarks
Divisions: Fakultas Sains Dan Teknologi > S1 Informatika
Depositing User: Kaprodi S1 Informatika UTY
Date Deposited: 07 May 2026 07:16
Last Modified: 07 May 2026 07:16
URI: http://eprints.uty.ac.id/id/eprint/19839

Actions (login required)

View Item View Item
UTY Open Access is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.