WORK SAFETY EQUIPMENT DETECTION SYSTEM USING YOLO ALGORITHM

Tridinata, Angga Nurman (2024) WORK SAFETY EQUIPMENT DETECTION SYSTEM USING YOLO ALGORITHM. Tugas Akhir thesis, University of Technology.

[img] Text
5200711031_Angga Nurman Triadinata.pdf
Download (130kB)

Abstract

ABSTRACT In industries such as construction, manufacturing, mining, and others, occupational safety and health (K3) is very important, therefore supervision in the use of occupational safety equipment is very important. Manual supervision will take a lot of time and is less efficient. The development of the era has supported the existence of automatic supervision technology through computer vision. YOLO (You Only look Once) is one of the object detection algorithms that is famous for its fast and accurate capabilities. This study aims to recognize work safety objects in the form of project helmets and project vests using YOLO. There are several stages that must be passed, namely data collection and labeling, YOLO model training, and system testing and evaluation. The success rate of detection of the use of K3 safety equipment is 100% with an average confidence value of 0.78. The level of lighting greatly affects the success rate of detection, for minimal lighting (lux 0) only a success rate of 10% is obtained. Keywords: Computer Vision, K3, YOLO

Item Type: Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir)
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Fakultas Sains Dan Teknologi > S1 Teknik Elektro
Depositing User: Kaprodi Teknik Elektro
Date Deposited: 07 Aug 2024 03:30
Last Modified: 07 Aug 2024 03:30
URI: http://eprints.uty.ac.id/id/eprint/15842

Actions (login required)

View Item View Item
UTY Open Access is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.