Prepoznavanje objekata primjenom dubokog učenja

undergraduate thesis

• Title (english): Object Detection Using Machine Learning
• Author: Tara Baće
• Mentor: Goran Delač (mentor)
• Committee member: Goran Delač (predsjednik povjerenstva)
• Committee member: Marin Kačan (član povjerenstva)
• Committee member: Ivan Grubišić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-06-27, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom istraživanju objašnjen je problem detekcije objekata u slikama te princip rada
jednoprolaznih detektora. Proveden je trening modela YOLOv5 na vlastitom skupu podataka
s ciljem razlikovanja glazbenih instrumenata. Uspoređeni su rezultati dobiveni
nad različitim ulaznim skupovima podataka te je detaljno opisan postupak vrednovanja
tih rezultata.

Abstract (english)

This research explains the problem of object detection in images and the working
principle of single-shot detectors. The YOLOv5 model was trained on a custom dataset
to distinguish musical instruments. The results obtained from different input datasets
were compared, and the evaluation process of these results was described in detail.

• Keywords: Yolo; detekcija objekata; duboko učenje
• Keywords (english): Yolo; object detection; deep learning
• Language: croatian
• URN:NBN: urn:nbn:hr:168:212650
• 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: Open access
• Created on: 2024-10-12 20:00:35