IDENTIFIKASI OBJEK SEKITAR BERBASIS ALGORITMA YOLO SEBAGAI INPUT SISTEM KENDALI KEMUDI PADA AUTONOMOUS ELECTRIC VEHICLE

VALIANT FANTHONY, IRVINE and Husin, Zaenal (2021) IDENTIFIKASI OBJEK SEKITAR BERBASIS ALGORITMA YOLO SEBAGAI INPUT SISTEM KENDALI KEMUDI PADA AUTONOMOUS ELECTRIC VEHICLE. Undergraduate thesis, Sriwijaya University.

	Text RAMA_03041281722032.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (9MB) | Request a copy
	Text RAMA_03041281722032_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (20MB) | Request a copy
Preview	Text RAMA_20201_03041281722032_0014025604_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (2MB) | Preview
	Text RAMA_20201_03041281722032_0014025604_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (348kB) | Request a copy
	Text RAMA_20201_03041281722032_0014025604_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (288kB) | Request a copy
	Text RAMA_20201_03041281722032_0014025604_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_20201_03041281722032_0014025604_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7kB) | Request a copy
	Text RAMA_20201_03041281722032_0014025604_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (76kB) | Request a copy
	Text RAMA_20201_03041281722032_0014025604_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (900kB) | Request a copy

Abstract

As smart vehicle technology develops, an autonomous electric vehicle is invented. The vehicle must be equipped with various sensors, one of which is a camera, which is working by providing visual input that is used to detect objects around the autonomous electric vehicle. Currently, there is no method that can be implemented in real time, so this research uses the YOLO (You Only Look Once) algorithm to detect objects in real time around the autonomous electric vehicle. The objects that will be detected by the autonomous electric vehicle in this research is limited to motorcycles and cars. The research results showed that the most compatible YOLO model for the system was the Tiny YOLOv4 model which was built with the help of the darknet framework. The result from the simulation experiment was the system is able to obtain a detection accuracy of 80% and capable to transmit information in a form of data location of the object to the microcontroller. From 10 times of testing, a success rate of 100% is obtained. YOLO was able to detect objects and provided input to the steering control system,. Meanwhile, to measure the distance of the object to the vehicle in real-time using the depth information method, an accuracy of 60% is obtained. Real-time testing will test whether the autonomous electric vehicle can avoid objects in front of it by inputting the detection results of the Tiny-YOLOv4 model object. The success rate of the system in real-time experiment is 100%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Autonomous Electric Vehicle, YOLO, Deteksi Objek, Image Processing
Subjects:	T Technology > T Technology (General) > T59.5 Automation T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7885-7895 Computer engineering. Computer hardware
Divisions:	03-Faculty of Engineering > 20201-Electrical Engineering (S1)
Depositing User:	Irvine Valiant Fanthony
Date Deposited:	02 Aug 2021 06:37
Last Modified:	15 Mar 2022 05:28
URI:	http://repository.unsri.ac.id/id/eprint/51099

Actions (login required)

View Item