Duboko učenje za automatizirano praćenje upotrebe zaštitne odjeće i opreme

master's thesis

• Title (english): Deep learning for Monitoring of Personal Protective Equipment Usage
• Author: Nika Rosandić
• Mentor: Vladimir Čeperić (mentor)
• Committee member: Vladimir Čeperić (predsjednik povjerenstva)
• Committee member: Zoran Kalafatić (član povjerenstva)
• Committee member: Mirko Poljak (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-16, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu razmatra se primjena dubokog učenja kod praćenja zaštitne odjeće i opreme,
primarno pri radu u industrijskim postrojenjima. Opisuje se korištenje dubokog učenja u
računalnom vidu i objašnjavaju metode dubokog učenja. Navode se već postojeća rješenja
problema automatiziranog praćenja zaštitne opreme i obrađuje se problem praćenja više
objekata. Detaljno se objašnjavaju korišteni algoritmi, YOLO i SORT, te prikazuju rezultati
učenja i testiranja korištene mreže. Mreža je učena na skupu slika ljudi u različitim
situacijama te zatim testirana u stvarnom vremenu putem kamere računala.

Abstract (english)

This thesis analyzes the use of deep learning in personal protective equipment tracking,
mainly in industrial plants and factories. It describes general use of deep learning in
computer vision and explains its methods. Existing solutions for personal protective
equipment monitoring are listed and the multiple object tracking problem is addressed.
Algorithms used in the solution, YOLO and SORT, are explained in detail, and the results
of learning and testing the network used are presented. The network was trained on a set of
images of people in different situations and then tested via computer camera.

• Keywords: duboko učenje; neuronske mreže; konvolucijske neuronske mreže; umjetna inteligencija; strojno učenje; zaštitna oprema; zaštitna odjeća; automatizirano praćenje; YOLO; SORT; Deep SORT
• Keywords (english): deep learning; neural networks; convolutional neural networks; artificial intelligence; machine learning; personal protective equipment; PPE; automatized tracking; YOLO; SORT; Deep SORT
• Language: croatian
• URN:NBN: urn:nbn:hr:168:404189
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 13:44:15