prikaz prve stranice dokumenta Detekcija objekata metodama strojnog učenja
  Download
PDF 713.16 KB
master's thesis
Detekcija objekata metodama strojnog učenja
Pula: University of Pula, 2020. urn:nbn:hr:137:616314
Bastijanić, Luka
University of Pula
Faculty of Informatics in Pula

Institutional repository: Digital Repository Juraj Dobrila University of Pula

Cite this document

Bastijanić, L. (2020). Detekcija objekata metodama strojnog učenja (Master's thesis). Pula: University of Pula. Retrieved from https://urn.nsk.hr/urn:nbn:hr:137:616314

Bastijanić, Luka. "Detekcija objekata metodama strojnog učenja." Master's thesis, University of Pula, 2020. https://urn.nsk.hr/urn:nbn:hr:137:616314

Bastijanić, Luka. "Detekcija objekata metodama strojnog učenja." Master's thesis, University of Pula, 2020. https://urn.nsk.hr/urn:nbn:hr:137:616314

Bastijanić, L. (2020). 'Detekcija objekata metodama strojnog učenja', Master's thesis, University of Pula, accessed 29 April 2024, https://urn.nsk.hr/urn:nbn:hr:137:616314

Bastijanić L. Detekcija objekata metodama strojnog učenja [Master's thesis]. Pula: University of Pula; 2020 [cited 2024 April 29] Available at: https://urn.nsk.hr/urn:nbn:hr:137:616314

L. Bastijanić, "Detekcija objekata metodama strojnog učenja", Master's thesis, University of Pula, Pula, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:137:616314

Metadata
TitleDetekcija objekata metodama strojnog učenja
Title (english)Machine learning methods for object detection
AuthorLuka Bastijanić
MentorDarko Etinger (mentor)
Committee memberNikola Tanković (predsjednik povjerenstva)
Committee memberDarko Etinger (član povjerenstva)
Committee memberSiniša Miličić (član povjerenstva)
GranterUniversity of Pula
(Faculty of Informatics in Pula)
Pula
Defense date and country2020-09-17, Croatia
Scientific / art field,
discipline and subdiscipline		SOCIAL SCIENCES
Information and Communication Sciences
Information Systems and Information Science
Abstract
Umjetna inteligencija je danas sve prisutnija u našem okruženju. Od autonomnih vozila do humanoidnih robota. Strojno učenje je potpodručje umjetne inteligencije koje se zadnjih godina sve više razvija. Ono nam pomaže u svakodnevnom životu rješavanjem nekih problema poput detekcije neželjene e-pošte, do onih nešto zahtjevnijih korištenjem većeg broja senzora poput pametnih usisivača koji pamte rute i prepreke. Važan dio strojnog učenja je i računalni vid. Ono što ga čini posebnim je to što omogućava strojevima da „progledaju“ te na taj način budu u mogućnosti rješavati neke probleme analizom onoga što takve zadaće prije nisu u stanju bili izvoditi. Vid je evolucijom čovjeku omogućio da prepozna objekte i okolinu bez puno muke stoga se ovaj rad bavi teorijom dostupnih alata za računalni vid. Bavi se detekcijom objekata odnosno dostupnim metodama unutar strojnog učenja. Obrađene su najpoznatije tehnike detekcije objekata, one koje se smatraju „ručnima“ i onim nešto modernijima poput dubokog učenja
Abstract (english)
Today artificial intelligence is everywhere around us. From autonomous vehicles to the humanoid robots. Machine learning is a subfield of the artificial intelligence which is developing more and more with each day. It has shown to be very helpfull for us by solving various problems, such as: e-Mail spam detection or robot vacuum cleaners which by using various sensors are remembering routes and detecting obstacles. Computer vision is important part of the machine learning. What makes it special is that we are „giving“ our machine possibility to see the world and by that fact we make it possible for them to perform some new tasks they weren't able to do before. This thesis is all about theory of available tools for computer vision. It is about available methods for object detection using machine learning. In this thesis we pass through some of the known techniques for the object detection which can be „hand-crafted“ methods or those more modern one like deep learning.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:137:616314
Study programmeTitle: Master in Informatics; specializations in: Master in Informatics, Master in Informatics, specialisation: teaching, Master in Informatics, Master in Informatics, specialisation: teaching
Course: Master in Informatics
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra informatike (magistar/magistra informatike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2022-05-11 08:54:12