magistrska naloga
Andrej Trunkl (Author), Pavle Boškoski (Mentor)

Abstract

cELES, družba za upravljanje z elektroenergetskim prenosnim sistemom, skrbi za nemoteno delovanje slovenskega električnega omrežja. Za zagotovitev nemotenega delovanja je treba izvajati redne preglede sredstev na omrežju. Ker so pregledi zamudni, se uporabljajo brezpilotna letala, s katerimi se fotografirajo sredstva na omrežjih. Količina tako posnetih fotografij je zelo velika, zato je ročno pregledovanje in prostorsko umeščanje teh posnetkov velik izziv. Cilj raziskave je izboljšati učinkovitost spremljanja stanja omrežja z razvojem metod za natančnejše in hitrejše zaznavanje ter analizo infrastrukture, kar bo izboljšalo zanesljivost in varnost omrežja.

Keywords

prostorsko umeščanje;zaznavanje infrastrukture;pred procesiranje fotografij;predpripravljeni modeli;prenos znanja;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: FIŠ - Faculty of Information Studies
Publisher: [A. Trunkl]
UDC: 004.92:004.85(043.2)
COBISS: 223132675 Link will open in a new window
Views: 139
Downloads: 15
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary abstract: ELES, the company responsible for managing the electricity transmission system, ensures the smooth operation of Slovenia’s electrical grid. To maintain uninterrupted service, regular inspections of network assets are necessary. Due to the time-consuming nature of these inspections, drones are used to photograph the network assets. The large volume of images captured presents a significant challenge for manual review and spatial placement. The aim of this research is to enhance the efficiency of network monitoring by developing methods for more accurate and faster detection and analysis of infrastructure, thereby improving the reliability and safety of the grid.
Secondary keywords: Spatial Placement;infrastructure detection;image preprocessing;Pre-trained Models;transfer learning;Univerzitetna in visokošolska dela;
Type (COBISS): Master's thesis/paper
Thesis comment: Fakulteta za informacijske študije v Novem mestu
Source comment: Na ov.: Magistrska naloga : študijskega programa druge stopnje;
Pages: XV, 83 str.
ID: 25738931