Određivanje prostornog pomaka s De Bruijnovim nizom

undergraduate thesis

• Title (english): Motion Determination Using De Bruijn Pattern
• Author: Marko Perić
• Mentor: Tomislav Pribanić (mentor)
• Committee member: Tomislav Pribanić (predsjednik povjerenstva)
• Committee member: Igor Sunday Pandžić (član povjerenstva)
• Committee member: Darko Vasić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2017-07-10, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

U ovom radu proučit ćemo osnovna svojstva de Bruijnovih nizova te kako nam ona mogu pomoći kod rješenja ovog problema. Pogledat ćemo osnovne prostore boja te kako ih opisujemo, koji prostori su nam od iznimne važnosti te njihove komponente potrebne za prepoznavanje boja. Upoznat ćemo se s OpenCV bibliotekom otvorenog kôda koja implementira različite metoda obrađivanja slika i analize računalnog vida. Objasnit ćemo Canny algoritam nalaženja rubova slike i korake koje OpenCV provodi za implementaciju tog algoritma. Konstruirat ćemo de Bruijnov niz prilagođen za računalni vid, a zatim ćemo pogledati rješenje kao računalni program te provesti eksperimentalnu evaluaciju. Na kraju ćemo pogledati rezultate dobivene eksperimentalnom evaluacijom.

Abstract (english)

In this paper we will examine the basic properties of de Bruijn sequence and how it can help us solve the problem of motion determination. We will look at the basic color spaces and how we describe them, which color spaces are of utmost importance to us and their component for color recognition. We will introduce OpenCV library which implements various methods for image processing and computer vision analysis. We will explain the Canny algorithm for finding the edges of the image and the steps that OpenCV conducts to implement this algorithm. We will construct a de Bruijn sequence suitable for computer vision, then look at the solution and conduct an experimental evaluation. Finally we will look at the results obtained by experimental evaluation.

• Keywords: Računalni vid; obrada slike; HSB prostor boja; RGB prostor boja; CMY prostoj boja; OpenCV; de Bruijn; Frank Ruskey; prostorni pomak; nalaženje rubova slike; Canny algoritam; obojenost; python
• Keywords (english): Computer vision; image processing; HSB color space; RGB color space; CMY color space; OpenCV; de Bruijn; Frank Ruskey; motion determination; edge detection; Canny algorithm; hue; python
• Language: croatian
• URN:NBN: urn:nbn:hr:168:898792
• 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: 2019-03-13 23:49:39