Prepoznavanje objekata primjenom strojnog učenja

undergraduate thesis

• Title (english): Object Detection Using Machine Learning
• Author: Ino Odak
• Mentor: Goran Delač (mentor)
• Committee member: Goran Delač (predsjednik povjerenstva)
• Committee member: Marin Vlaić (član povjerenstva)
• Committee member: Ivan Mikulić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-01, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom završnom radu izneseni su osnovni pojmovi i problemi računalnog vida. Naglasak je bio na zadatku prepoznavanja objekata te YOLO algoritmu za rješavanje ovog zadataka. Analizirani su temeljni problemi zadatka prepoznavanja objekata te su diskutirani različiti pristupi rješavanja ovog problema zajedno s njihovim prednostima i nedostatcima. Dodatno, Analizirana je YOLO familija modela s naglaskom na njihovoj funkciji gubitka, arhitekturi te postupcima treniranja i zaključivanja. Rezultat analize je implementacija računalnih programa koji demonstriraju funkcionalnosti nekih od navedenih modela napisanih u programskom jeziku Python.

Abstract (english)

The goal of this bachelor's thesis was to introduce fundemental concepts and problems of computer vision. The main focus of analysis was the task of object detection along with YOLO family of models that are used to solve this problem. Various approaches to solving the problem of object detection were discussed along with their respective benefits and drawdowns. Additionaly YOLO family of models was analysed with the focus being their architecture, loss function, traing procedure, and inference. The result of this analysis was the implementation of Python programes that demonstrate the main functionalities of some of theese models.

• Keywords: prepoznavanje objekata; strojno učenje; YOLO algoritam; lokalizacija objekata; klasifikacija objekata; računalni vid
• Keywords (english): object detection; machine learning; YOLO algorithm; object localization; object classification; computer vision
• Language: croatian
• URN:NBN: urn:nbn:hr:168:805479
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-15 10:55:59