Analiza satelitskih snimaka za procjenu šumarskih parametara

undergraduate thesis

• Title (english): Satellite image analysis for assessment of forestry parameters
• Author: Martin Čukić
• Mentor: Marko Subašić (mentor)
• Committee member: Marko Subašić (predsjednik povjerenstva)
• Committee member: Roko Franetović (član povjerenstva)
• Committee member: Franko Šikić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-06-20, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Implementacijom U-Net arhitekture duboke neuronske mreže istražene su metode
za segmentaciju satelitskih snimaka šumskog podrucja. Pripremljen je odgovarajući
skup ulaznih podataka i provedene su razne modifikacije neuronske mreže. Analizirani
su rezultati evaluacije uspješnosti semantičke segmentacije.

Abstract (english)

By implementing the U-Net architecture of a deep neural network, methods for
the segmentation of satellite images of a forest area were investigated. An appropriate set of input data was prepared and various modifications of the neural network
were carried out. The evaluation results of the success of semantic segmentation were
analyzed.

• Keywords: segmentacija; U-Net; mreža; slike; maske; preciznost; podatci; konfiguracija; treniranje; evaluacija; analiza
• Keywords (english): segmentation; U-Net; network; images; masks; accuracy; data; configuration; training; evaluation; analysis
• Language: croatian
• URN:NBN: urn:nbn:hr:168:905196
• 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: Open access
• Created on: 2025-02-25 13:23:44