Sustav za praćenje objekata u video sekvencama

undergraduate thesis

• Title (english): System for tracking objects in video sequences
• Author: Andrej Jurić
• Mentor: Zoran Kalafatić (mentor)
• Committee member: Zoran Kalafatić (predsjednik povjerenstva)
• Committee member: Alan Jović (član povjerenstva)
• Committee member: Zvonimir Pavlić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2016-09-07, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Praćenje objekata zahtjevna je, ali brzo razvijajuća grana računalne znanosti koja svoju povijest temelji na svega 40-ak godina aktivnog istraživanja. Kao rezultat, nekoć nazamisliva tehnologija danas se svakodnevno koristi u uređajima i sustavima diljem svijeta. Popularni algoritmi detekcije i praćenja objekata danas uključuju histograme boja, oduzimanje pozadine, optički tok, te varijacije MeanShift algoritma. MeanShift algoritam jest algoritam pronalaska mjesta najveće gustoće unutar nakupine točaka u d-dimenzionalnom vektorskom prostoru. Kao takav MeanShift algoritam svoje mjesto pronalazi u praćenju objekata gdje postupno iterirajući kroz sliku kao 2-dimenzionalni vektorski prostor algoritam pronalazi ciljani objekt.

Abstract (english)

Object tracing is demanding but fast evolving branch of computer science that traces its history no more than 40 years back from now. As a result, once unimaginable technology is nowadays used in gadgets and systems all around the world. Popular detection and tracking algorithms today include color histograms, background substraction, optical flow and MeanShift algorithm variations. Meanshift algorithm is clustering algorithm working on set of points inside d-dimensional vector space. As such MeanShift algorithm found its place in object tracking where it finds objects of interest by iterating through picture as if it were 2-dimensional vector space.

• Keywords: Računalni vid; Praćenje objekata; Histogrami boja; MeanShift algoritam
• Keywords (english): Computer vision; Object tracking; Color histograms; MeanShift algorithm
• Language: croatian
• URN:NBN: urn:nbn:hr:168:162800
• 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: 2018-02-06 09:30:38