Primjena umjetne inteligencije u predobradi fotogrametrijskih snimki

master's thesis

• Title (english): Application of artificial intelligence in the preprocessing of photogrammetric images
• Author: Izabela Nikolina Gusić Janjić
• Mentor: Dubravko Gajski (mentor)
• Committee member: Andrija Krtalić (predsjednik povjerenstva)
• Committee member: Vanja Miljković (član povjerenstva)
• Granter: University of Zagreb; Faculty of Geodesy; Zagreb
• Defense date and country: 2024-09-20, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Geodesy; Photogrammetry and Remote Sensing

Abstract

Ovaj rad je obuhvatio primjenu umjetne inteligencije kao alata za unapređenje predobrade fotogrametrijskih snimki. Korištenjem raznih metoda učenja, UI može automatski detektirati i ispraviti greške, filtrirati šum, poboljšati kvalitetu snimki, te ukloniti neželjene objekte. Obavljena je praktična primjena algoritama na fotogrametrijskim snimkama nastalim u nepovoljnim uvjetima kao što su kiša, magla, snijeg, loše osvjetljenje ili objekta koji zaklanja dio scene. Prikazani su rezultati 3D modela izrađenih od originalnih i obrađenih snimki. Vidljiva je i važnost odabira aplikacije preko koje će se obrada izvršavati, kao i kombiniranje više algoritama kako bi se postigli bolji rezultati. Rezultati pokazuju da umjetna inteligencija značajno smanjuje vrijeme predobrade i povećava objektivnost u procesu odluke te povećava estetičnost bitnu za prvi dojam.

Abstract (english)

This work encompasses the application of artificial intelligence as a tool for improving the pre-processing of photogrammetric images. Using various learning methods, AI can automatically detect and correct errors, filter noise, improve image quality, and remove unwanted objects. A practical application of algorithms on photogrammetric images taken in adverse conditions such as rain, fog, snow, poor lighting or objects obscuring part of the scene was performed. The results of 3D models created from original and processed images are presented. The importance of selecting the application through which the processing will be performed, as well as combining multiple algorithms to achieve better results, is also visible. The results show that artificial intelligence significantly reduces pre-processing time, increases objectivity in the decision-making process and enhances aesthetics important for the first impression.

• Keywords: fotogrametrija; metode učenja; predobrada; snimke; umjetna inteligencija
• Keywords (english): photogrammetry; learning methods; preprocessing; images; artificial intelligence
• Language: croatian
• URN:NBN: urn:nbn:hr:256:257699
• Study programme: Title: Geodesy and Geoinformatics; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka geodezije i geoinformatike (magistar/magistra inženjer/inženjerka geodezije i geoinformatike)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Access restricted to students and staff of home institution
• Created on: 2024-09-12 20:29:34