Deteksi Warna Lampu Lalu Lintas Menggunakan YOLOV8

Kurniawan, Arief Yoga (2025) Deteksi Warna Lampu Lalu Lintas Menggunakan YOLOV8. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 07211840000057-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (15MB) | Request a copy

Abstract

Kemacetan lalu lintas dan tingginya angka kecelakaan di perkotaan memerlukan solusi inovatif, salah satunya adalah penerapan teknologi kendaraan otonom yang menggunakan kecerdasan buatan (AI) untuk mendeteksi sinyal lampu lalu lintas. YOLOv8 menawarkan kemampuan deteksi objek secara cepat dan akurat, sehingga cocok untuk diaplikasikan dalam lingkungan lalu lintas yang dinamis. Namun, tantangan baru muncul dari desain lampu lalu lintas modern, di mana dua lampu dapat menyala bersamaan, seperti merah dan kuning, yang memerlukan sistem deteksi lebih adaptif. Penelitian ini berfokus pada penggunaan YOLOv8 untuk mendeteksi lampu lalu lintas dalam berbagai kondisi, termasuk situasi kompleks tersebut, guna mendukung kendaraan otonom dalam mengambil keputusan yang lebih aman dan akurat. Diharapkan, implementasi ini dapat berkontribusi pada sistem transportasi yang lebih cerdas dan responsif, sehingga mengurangi kemacetan dan meningkatkan keselamatan jalan di perkotaan.
======================================================================================================================================
Traffic congestion and high accident rates in urban areas require innovative solutions, one of which is the application of autonomous vehicle technology that uses artificial intelligence (AI) to detect traffic light signals. YOLOv8 offers fast and accurate object detection capabilities, making it suitable for application in dynamic traffic environments. However, new challenges arise from the design of modern traffic lights, where two lights can be on simultaneously, such as red and yellow, which requires a more adaptive detection system. This study focuses on the use of YOLOv8 to detect traffic lights in various conditions, including these complex situations, to support autonomous vehicles in making safer and more accurate decisions. It is hoped that this implementation can contribute to a smarter and more responsive transportation system, thereby reducing congestion and improving road safety in urban areas.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	visi Komputer, Deteksi Objek, Kendaraan Otonom,Deep Learning,YOLO,Computer Vision,Object detection,Autonomous Vehicles
Subjects:	T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques. Image analysis--Data processing. T Technology > TL Motor vehicles. Aeronautics. Astronautics > TL152.8 Vehicles, Remotely piloted. Autonomous vehicles.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Computer Engineering > 90243-(S1) Undergraduate Thesis
Depositing User:	Arief Yoga Kurniawan
Date Deposited:	29 Jul 2025 03:42
Last Modified:	29 Jul 2025 04:01
URI:	http://repository.its.ac.id/id/eprint/122524

Actions (login required)

View Item