Semantička segmentacija velikih satelitskih slika

undergraduate thesis

• Title (english): Semantic segmentation of large satellite images
• Author: Marko Haralović
• Mentor: Siniša Šegvić (mentor)
• Committee member: Siniša Šegvić (predsjednik povjerenstva)
• Committee member: Marin Kačan (član povjerenstva)
• Committee member: Iva Sović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-07-08, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovome je radu dan pregled arhitektura i performansi dubokih modela koji koriste
poduzorkovanu reprezentaciju uzorka za učenje u zadacima guste predikcije, odnosno na
zadacima semantičke segmentacije slike. Opisani su provedeni eksperimenti te su sažeto
prikazana vrednovanja različitih segmentacijskih arhitektura.

Abstract (english)

This paper provides an overview of the architectures and performances of deep models that
use a subsampled image representation for learning in dense prediction tasks, specifically
in image semantic segmentation tasks. The experiments conducted are described, and
evaluations of various segmentation architectures are presented.

• Keywords: računalni vid; duboko učenje; semantička segmentacija; poduzorkovana reprezentacija.
• Keywords (english): computer vision; deep learning; semantic segmentation; subsampled image representation.
• Language: croatian
• URN:NBN: urn:nbn:hr:168:126743
• 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: 2024-10-12 20:46:41