Smart Traffic Light Menggunakan Kamera Berbasis Yolo Dengan Algoritma Deep Reinforcement Learning

Tampubolon, Yosua Marthin Hawila (2022) Smart Traffic Light Menggunakan Kamera Berbasis Yolo Dengan Algoritma Deep Reinforcement Learning. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 07111840000061-Undergraduate_Thesis.pdf Restricted to Repository staff only Download (3MB)

Abstract

Kemacetan merupakan permasalahan umum yang sering terjadi di kota-kota besar. Kemacetan menimbulkan banyak kerugian seperti dari segi waktu, ekonomi, hingga psikologi pengguna jalan. Salah satu penyebab kemacetan adalah lampu lalu lintas yang tidak adaptif terhadap dinamika arus lalu lintas. Tugas akhir ini mencoba memecahkan permasalahan tersebut dengan pendekatan Reinforcement Learning yang digabung dengan simulator lalu lintas SUMO (Simulation of Urban Mobility). Data yang digunakan merupakan data real video persimpangan KD Cowek, Surabaya. Data video tersebut diolah menggunakan algoritma YOLO yang akan mendeteksi dan menghitung kendaraan. Output dari pengolahan video tersebut yang akan digunakan dalam Reinforcement Learning. Hasil dari Reinforcement Learning adalah jumlah panjang antrean lalu lintas pada jam 06.00 - 09.00 miliki rata-rata sebesar 106 kendaraan.
==============================================================================================================================
Congestion is a common problem that often occurs in big cities. Congestion causes a lot of losses, such as in terms of time, economy, to the psychology of road users. One of the causes of congestion is traffic lights that are not adaptive to the dynamics of traffic flow. This final project tries to solve this problem using a Reinforcement Learning approach combined with a SUMO (Simulation of Urban Mobility) traffic simulator. The data used is the real video data of the KD Cowek intersection, Surabaya. The video data is processed using the YOLO algorithm which will detect and count vehicles. The output of the video processing will be used in Reinforcement Learning. The result of Reinforcement Learning is that the total length of the traffic queue at 06.00-09.00 has an average of 106 vehicles.

Item Type:	Thesis (Other)
Additional Information:	RSE 621.367 Tam s-1 2022
Uncontrolled Keywords:	smart traffic light. reinforcement learning. YOLO. smart traffic light. reinforcement learning. YOLO.
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Electrical Engineering > 20201-(S1) Undergraduate Thesis
Depositing User:	Mr. Marsudiyana -
Date Deposited:	12 Jun 2026 03:47
Last Modified:	12 Jun 2026 03:47
URI:	http://repository.its.ac.id/id/eprint/133764

Actions (login required)

View Item