Usporedba metoda dubokog učenja za detekciju objekata u sklopu strojnog vida

undergraduate thesis

• Title (english): Comparison of deep learning methods for object detection in machine vision
• Author: Kristian Vuletić
• Mentor: Tomislav Stipančić (mentor)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2024-02-28, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mechanical Engineering

Abstract

U svijetu detekcije objekata došlo je do velikog porasta popularnosti metoda dubokog učenja, u tijeku je ubrzani razvoj novih metoda. U sklopu rada identificirani su temeljni pristupi tih metoda, sličnosti i razlike identificiranih pristupa te su opisane razne metode razvijene kroz povijest. Nakon toga, proveden je eksperiment u kojem su dvije metode trenirane i testirane na javnim bazama podataka.

Abstract (english)

In the world of object detection there has been a big surge in popularity of deep learning
methods, new methods are being developed at a very fast pace. This paper identifies the
fundamental approaches of those methods, their similarities and differences and then describes
the various methods developed throughout history. After that, and experiment is conducted in
which two methods are trained and tested on publically available databases.

• Keywords: detekcija objekata; duboko učenje
• Keywords (english): object detection; deep learning
• Language: croatian
• URN:NBN: urn:nbn:hr:235:144931
• Study programme: Title: Mechanical Engineering; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2024-02-23 16:17:22