20.500.12556/RUL-175484 Uporaba tlorisnih odtisov stavb za segmentacijo in atributiranje poligonske 3D mreže magistrsko delo Application of Building Footprints for the Segmentation and Attribution of a 3D Mesh master thesis V magistrski nalogi preizkusimo segmentacijo in atributiranje stavb v poligonski 3D mreži na podlagi tlorisnih odtisov stavb. Večino dela opravimo v programu ArcGIS Pro. Izhodiščna podatka naloge sta fotogrametrični oblak točk in poligonska 3D mreža izbranega območja v Ljubljani, izdelana iz podatkov poševnega aerofotografiranja. Za segmentacijo uporabimo tlorisne odtise stavb, pridobljene z ročno vektorizacijo, klasifikacijo fotogrametričnega oblaka točk in iz javno dostopnih virov. Preizkusili in opisali smo pet nizov rezultatov klasifikacije stavb v oblaku točk. V programu Matlab smo naredili oceno kakovosti klasifikacije oblaka točk. Postopek za pridobivanje tlorisnih odtisov stavb smo opisali za devet različnih primerov in naredili oceno kakovosti odtisov stavb. Atributne podatke smo prav tako pridobili iz javno dostopnih virov. Za segmentacijo in atributiranje poligonske 3D mreže se najbolje izkažejo ročno vektorizirani odtisi stavb. Dobre rezultate dosežemo tudi z odtisi stavb, pridobljenimi z ročno in avtomatsko klasifikacijo oblaka točk ter prenosom klasifikacije iz georeferenciranega in klasificiranega oblaka točk iz projekta Cikličnega laserskega skeniranja Slovenije. Ugotovili smo, da je kakovost segmentacije in atributiranja poligonske 3D mreže odvisna od kakovosti odtisov stavb. Kljub omejitvam naloga prikazuje možen način integracije poligonskih 3D mrež v sodobna GIS okolja ter daje podlago za nadaljnje raziskave na področju avtomatskega zaznavanja stavb. In this master’s thesis, we examine the segmentation and attribution of a 3D mesh based on building footprints. Most of the work is carried out in ArcGIS Pro. The primary datasets used are a photogrammetric point cloud and 3D mesh of a selected area in Ljubljana, created from oblique aerial imagery. Segmentation is performed using building footprints obtained through manual vectorization, classification of the photogrammetric point cloud, and publicly available sources. We tested and described five sets of building classification results in the point cloud. The quality of the point cloud classification was evaluated in Matlab. The process of obtaining building footprints is described for nine different cases, and their quality was evaluated. Attribute data were also obtained from publicly available sources. Manual vectorization of building footprints proved to be the most effective method for segmenting and attributing the 3D mesh. Good results were also achieved with building footprints derived from manual and automatic point cloud classification, as well as from transferring classification from a georeferenced and classified point cloud obtained through the project of national Cyclical lidar survey of Slovenia. We found that the quality of segmentation and attribution of the 3D mesh depends on the quality of the building footprints. Despite its limitations, the thesis demonstrates a potential approach for integrating 3D meshes into modern GIS environments and provides a basis for further research in the field of automatic building detection. magistrska dela geodezija in geoinformatika poligonska 3D mreža tlorisni odtisi stavb fotogrametrični oblak točk klasifikacija segmentacija master thesis geodesy and geoinformatics 3D mesh building footprints photogrammetric point cloud classification segmentation true false false [M. Krebs] Slovenski jezik Angleški jezik Magistrsko delo/naloga 2025-10-29 08:45:21 2025-10-29 08:45:30 2025-12-11 03:56:06 0000-00-00 00:00:00 2025 0 Ljubljana 2025 Ljubljana 1 spletni vir (1 datoteka PDF (XII, 62 str.)) 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 528.73:004.42(043.2) 175610 255456259 20217.pdf 20217.pdf 1 9301F16727DF91B06233B88FE95A9E4B 9392c1f0ca9cfb5cc6c34e284bd3a71f34468ac16eecaa46b75d541d321ab129 f1858855-b49a-11f0-9328-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=221085 Fakulteta za gradbeništvo in geodezijo 0 0 0