PENDETEKSIAN OBJEK UNTUK PENYANDANG TUNANETRA MENGGUNAKAN METODE YOLO

SHAFIYYURRAHMAN, ASYRAF and Kurniati, Rizki and Arsalan, Osvari (2023) PENDETEKSIAN OBJEK UNTUK PENYANDANG TUNANETRA MENGGUNAKAN METODE YOLO. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021381924130.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (27MB) | Request a copy
	Text RAMA_55201_09021381924130_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (11MB) | Request a copy
	Text RAMA_55201_09021381924130_0012079104_0028068806_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (639kB)
	Text RAMA_55201_09021381924130_0012079104_0028068806_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (616kB) | Request a copy
	Text RAMA_55201_09021381924130_0012079104_0028068806_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021381924130_0012079104_0028068806_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (412kB) | Request a copy
	Text RAMA_55201_09021381924130_0012079104_0028068806_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (21MB) | Request a copy
	Text RAMA_55201_09021381924130_0012079104_0028068806_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (110kB) | Request a copy
	Text RAMA_55201_09021381924130_0012079104_0028068806_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (84kB) | Request a copy
	Text RAMA_55201_09021381924130_0012079104_0028068806_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy

Abstract

A visually impaired individual faces limitations in mobility, which can affect their ability to communicate and interact with the surrounding environment. External help such as human assistance, trained dogs, and white canes are commonly used, but the availability and dependence on such assistance pose challenges. This research develops a mobile-based application that employs the You Only Look Once (YOLO) method as a tool for the visually impaired. The application aims to assist them in navigating by detecting obstacles and providing audio directions to the user. The objects targeted for detection in this study include park benches, poles, pots, and trees. The research conducted experiments with various configurations, including epochs 50, 100, and 200, and batch sizes of 16, 32, and 64. The best results were achieved with the combination of epoch 100 and batch size 64, yielding an mAP50 value of 83.20%. Keywords : Object Detection, You Only Look Once (YOLO), Visually Impaired, Accessibility, Mobility.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Deteksi Objek, You Only Look Once (YOLO), Tunanetra, Aksesibilitas, Mobilitas
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Asyraf Shafiyyurrahman
Date Deposited:	03 Aug 2023 07:22
Last Modified:	03 Aug 2023 07:22
URI:	http://repository.unsri.ac.id/id/eprint/125485

Actions (login required)

View Item