Klasifikacija termalnih infracrvenih snimaka iz zraka

master's thesis

• Title (english): Aerial Thermal Images Classification
• Author: Mislav Vrabec
• Mentor: Jurica Ivošević (mentor)
• Committee member: Tomislav Radišić (predsjednik povjerenstva)
• Committee member: Doris Novak (član povjerenstva)
• Committee member: Tino Bucak (član povjerenstva)
• Granter: University of Zagreb; Faculty of Transport and Traffic Sciences; (Division of Aeronautics); (Department of Aeronautics); Zagreb
• Defense date and country: 2020-12-01, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Traffic and Transport Technology

Abstract

Zadatak ovog diplomskog rada opisati je primjenu Matlabovih alata u svrhu klasifikacije termalne dugovalne snimke. Konačan proizvod koji proizlazi iz klasifikacije, video je koji prikazuje označavanje objekata od interesa (pčela) u pokretu. U prvom dijelu rada dan je uvod u svojstva elektromagnetnog zračenja, elektromagnetnog spektra kao i fizikalnih zakona koje to zračenje prati u interakcijama sa atmosferom i ostalim fizikalnim površinama. Analizirano je infracrveno zračenje i njegovi koncepti. Nakon toga, dane su teorijske osnove digitalne klasifikacije snimaka, nadzirane i nenadzirane klasifikacije. U praktičnom dijelu rada razvijen je programski kod u programskom jeziku Matlab, analizirani su rezultati dobiveni njegovom primjenom te procijenjena točnost klasifikacije termalnih infracrvenih snimaka iz zraka.

Abstract (english)

The task of this thesis is to describe the application of Matlab tools for the purpose of thermal images classification. The final product resulting from the classification, is a video that shows the labeling of objects of interest (bees) in motion. In the first part of the thesis, an introduction to the properties of electromagnetic radiation is given, as well as the electromagnetic spectrum with the physical laws it abides to in the interactions with the atmosphere and other physical surfaces. Infrared radiation and its concepts are analyzed. After that, the theoretical foundations of digital image classification, as well as supervised and unsupervised classifications are given. In the practical part of the thesis, the program code in the Matlab programming language was developed, the results obtained by its application were analyzed, and the accuracy of classification of aerial thermal infrared images was assessed.

• Keywords: daljinska istraživanja termalne infracrvene snimke; klasifikacija snimaka; Matlab; pčele
• Keywords (english): remote sensing; thermal infrared images; images classification; Matlab; bees
• Language: croatian
• URN:NBN: urn:nbn:hr:119:519965
• Study programme: Title: Aeronautics; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka aeronautike (magistar/magistra inženjer/inženjerka aeronautike)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2020-12-08 11:42:11