Prototipe sistem pengendali lampu high beam pada kendaraan motor menggunakan Artificial Intelligence dengan metode You Only Look Once

Fauzi, Aldi Muhamad (2024) Prototipe sistem pengendali lampu high beam pada kendaraan motor menggunakan Artificial Intelligence dengan metode You Only Look Once. Sarjana thesis, UIN Sunan Gunung Djati Bandung.

Preview	Text (COVER) 1_cover.pdf Download (74kB) | Preview
Preview	Text (DAFTAR ISI) 3_daftarisi.pdf Download (123kB) | Preview
Preview	Text (ABSTRAK) 2_abstrak.pdf Download (25kB) | Preview
Preview	Text (BAB I) 4_bab1.pdf Download (66kB) | Preview
	Text (BAB II) 5_bab2.pdf Restricted to Registered users only Download (761kB) | Request a copy
	Text (BAB III) 6_bab3.pdf Restricted to Registered users only Download (28kB) | Request a copy
	Text (BAB IV) 7_bab4.pdf Restricted to Registered users only Download (495kB) | Request a copy
	Text (BAB V) 8_bab5.pdf Restricted to Registered users only Download (706kB) | Request a copy
	Text (BAB VI) 9_bab6.pdf Restricted to Registered users only Download (195kB) | Request a copy
	Text (DAFTAR PUSTAKA) 10_daftarpustaka.pdf Restricted to Registered users only Download (96kB) | Request a copy
	Text (LAMPIRAN) DRAFT TA_Aldi Muhamad Fauzi-2-80-88.pdf Restricted to Repository staff only Download (114kB) | Request a copy

Abstract

INDONESIA: Perkembangan teknologi terkini telah menghasilkan berbagai sistem yang mempermudah dan meningkatkan keselamatan dalam tugas sehari-hari pengguna, termasuk di industri otomotif. Kendaraan sebagai sarana transportasi yang umum digunakan telah melalui transformasi signifikan, dari sekadar alat transportasi menjadi platform yang mengintegrasikan teknologi canggih untuk kenyamanan dan keamanan pengendara. Penelitian ini berfokus pada pengembangan prototipe sistem pengendali otomatis lampu utama kendaraan bermotor menggunakan metode deteksi objek You Only Look Once (YOLO) berbasis Deep Learning, dengan mikrokontroler Arduino Uno R3 sebagai pengendali utama. Sistem ini dirancang untuk mengurangi risiko kecelakaan yang disebabkan oleh pancaran lampu yang tidak terkontrol, terutama saat bertemu pengendara lain di jalan. Dengan memanfaatkan kamera dan algoritma YOLOv5, sistem mampu secara otomatis beralih antara lampu jauh dan lampu dekat berdasarkan deteksi kendaraan lain di sekitar. Pengujian menggunakan kamera internal dan eksternal menunjukkan performa yang sangat baik, dengan akurasi, presisi, recall, dan F1-score mencapai 100% dalam beberapa skenario uji. Hasil penelitian ini menunjukkan bahwa sistem yang dikembangkan dapat secara efektif meningkatkan keselamatan berkendara pada malam hari dengan mendeteksi objek secara cepat dan akurat. ENGLISH: Recent technological developments have produced various systems that simplify and increase safety in users' daily tasks, including in the automotive industry. Vehicles as a commonly used means of transportation have undergone a significant transformation, from being just a means of transportation to becoming a platform that integrates advanced technology for driver comfort and safety. This research focuses on developing a prototype of an automatic headlight control system for motorized vehicles using the Deep Learningbased You Only Look Once (YOLO) object detection method, with the Arduino Uno R3 microcontroller as the main controller. This system is designed to reduce the risk of accidents caused by uncontrolled light beams, especially when meeting other drivers on the road. By utilizing the camera and the YOLOv5 algorithm, the system is able to automatically switch between high beam and low beam based on the detection of other vehicles nearby. Tests using internal and external cameras show excellent performance, with accuracy, precision, recall and F1-score reaching 100% in several test scenarios. The results of this research show that the system developed can effectively improve driving safety at night by detecting objects quickly and accurately.

Actions (login required)

View Item