Procjena dubine podudaranjem stereo slika

undergraduate thesis

• Title (english): Depth estimation via stereo matching
• Author: Oliver Ozvačić
• Mentor: Ivan Marković (mentor)
• Committee member: Ivan Marković (član povjerenstva)
• Committee member: Vlaho-Josip Štironja (član povjerenstva)
• Committee member: Jelena Gregorić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-07-10, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Ovaj završni rad istražuje procjenu dubine stereoskopskom rekonstrukcijom, ključnu za trodimenzionalni vid u računalnim sustavima. Opisane su teorijske osnove stereo vizije, uključujući epipolarnu geometriju i rektifikaciju slika. Implementirane su i eksperimentalno verificirane metode procjene dubine koristeći OpenCV i Kornia. Analizirani su lokalni i globalni pristupi, pri čemu su lokalne metode jednostavne i brze, ali ograničene točnosti, dok globalne i napredne metode pružaju veću točnost i robusnost uz veću računalnu složenost. Rad pruža temelje za daljnja istraživanja i razvoj u području računalnog vida.

Abstract (english)

This thesis explores depth estimation through stereoscopic reconstruction, crucial for three-dimensional vision in computer systems. It covers the theoretical foundations of stereo vision, including epipolar geometry and image rectification. Depth estimation methods using OpenCV and Kornia were implemented and experimentally verified. Local and global approaches were analyzed, with local methods being simple and fast but limited in accuracy, while global and advanced methods provided higher accuracy and robustness at the cost of greater computational complexity. The work lays the foundation for further research and development in the field of computer vision.

• Keywords: procjena dubine; stereo vizija; epipolarna geometrija; rektifikacija slika; OpenCV; Kornia; računalni vid
• Keywords (english): depth estimation; stereo vision; epipolar geometry; image rectification; OpenCV; Kornia; computer vision
• Language: croatian
• URN:NBN: urn:nbn:hr:168:920476
• 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: 2024-10-12 21:44:17