Vizijski sustav za klasifikaciju objekata temeljen na YOLOv8 modelu

master's thesis

• Title (english): A vision system for object classification based on the YOLOv8 model
• Author: Anamarija Stepinac
• Mentor: Tomislav Stipančić (mentor)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2024-01-25, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mechanical Engineering

Abstract

Računalni vid je područje umjetne inteligencije, odnosno dubokog učenja, koje računalnim sustavima daje mogućnost vida. Za primjenu računalnog vida su razvijeni algoritmi za izvršavanje zadataka na slikama i videima, poput prepoznavanja objekata, klasifikacije i praćenja objekata. U radu je iznesena teorijska osnova potrebna za razumijevanje algoritama računalnog vida te je potkrijepljena primjerom u kojem je korišten algoritam YOLOv8. Algoritam je treniran i provjeren na označenom skupu podataka, a zatim testiran za prepoznavanje, klasifikaciju i praćenje na neviđenom primjeru.

Abstract (english)

Computer vision is an area of artificial intelligence, or rather deep learning, that gives computer systems the ability to see. Computer vision algorithms have been developed for performing tasks on images and videos, such as object recognition, classification and object tracking. The paper presents the theoretical basis necessary for understanding computer vision algorithms and is supported by an example in which the YOLOv8 algorithm was used. The algorithm was trained and validated on a labelled dataset and then tested for recognition, classification, and tracking on an unseen example.

• Keywords: umjetna inteligencija; duboko učenje; računalni vid; prepoznavanje objekata; klasifikacija; praćenje objekata; YOLOv8
• Keywords (english): artificial intelligence; deep learning; computer vision; object detection; classification; object tracking; YOLOv8
• Language: croatian
• URN:NBN: urn:nbn:hr:235:873965
• Study programme: Title: Mechanical Engineering; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka strojarstva (magistar/magistra inženjer/inženjerka strojarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2024-01-23 13:18:25