diplomsko delo Visokošolskega strokovnega študijskega programa I. stopnje Strojništvo
Jan Štefin (Avtor), Janko Slavič (Mentor), Matija Jezeršek (Komentor)

Povzetek

V diplomski nalogi so predstavljene meritve strehe, ki so bile izmerjene z uporabo brezpilotnega letalnika in lastne Python kode. Ozadje meritev temelji na določanju koordinat preko hitrosti in časa. Preko metode Scale-Invariant Feature Transform so glede na okoliške točke na dveh različnih slikah bili poiskani ujemajoči se deli ter odstranjene točke, neskladne z izbranim modelom slikanja z več pogledi. Poiskane oziroma izračunane so bile tudi rotacijske in translacijske matrike in s pomočjo triangulacije je rekonstruirana lega opazovanih točk v 3D koordinatnem sistemu. Na koncu je bila določena razdalja le med izbranimi točkami, ki ležijo na robu strehe. Rezultat diplomske naloge so meritve strehe, ki jih s pomočjo Pyhton kode program samodejno določi, odstopanja od dejanskih meritev pa v povprečji niso večja kot pol metra.

Ključne besede

diplomske naloge;brezpilotni letalnik;računalniški vid;umetna inteligenca;meritve strehe;OpenCV;SIFT;triangulacija;

Podatki

Jezik: Slovenski jezik
Leto izida:
Tipologija: 2.11 - Diplomsko delo
Organizacija: UL FS - Fakulteta za strojništvo
Založnik: [J. Štefin]
UDK: 629.014.9:004.8:528.3(043.2)
COBISS: 85014019 Povezava se bo odprla v novem oknu
Št. ogledov: 515
Št. prenosov: 104
Ocena: 0 (0 glasov)
Metapodatki: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Ostali podatki

Sekundarni jezik: Angleški jezik
Sekundarni naslov: Geometric measurements of the housing roof using an unmanned aerial vehicle
Sekundarni povzetek: Our research presents an image-based rooftop measurement system used in an unmanned aerial vehicle controlled by Python code. The background of our measurements was based on spatial data reconstruction, using multiple images taken by an unmanned aerial vehicle, while taking into consideration the known positions of the aircraft. Through the ScaleInvariant Feature Transform method, matching parts in two different images were found, taking into consideration the surrounding points, while disturbing points were removed. The rotation and translation matrices were calculated and triangulation to reconstruct the position of the observed points in a 3D coordinate system was used. Finally, the points located at the very edge of the roof were selected and by that the distance between them was determined. The final task resulted in roof measurements that are automatically determined by the software using Python code, with deviations from ground-truth averaging no more than half a metre.
Sekundarne ključne besede: thesis;unmanned aeriel vehicle;computer vision;artificial intelligence;roof measurement;scale-invariant feature transform;open source computer vison libary;triangulation;
Vrsta dela (COBISS): Diplomsko delo/naloga
Študijski program: 0
Konec prepovedi (OpenAIRE): 1970-01-01
Komentar na gradivo: Univ. v Ljubljani, Fak. za strojništvo
Strani: XXII, 42, [2] str.
ID: 13836595