Segmentacija oblaka točk z Gaussovo sfero

diplomska naloga

Blaž Lipuš (Author), Mojca Kosmatin Fras (Mentor), Dejan Grigillo (Co-mentor), Tilen Urbančič (Co-mentor)

Abstract

Pridobivanje prostorskih podatkov z laserskim skeniranjem se v zadnjih letih hitro razvija. Oblaki točk, ki so primarni rezultat obdelave opazovanj laserskega skeniranja, so uporabni pri modeliranju skeniranih objektov ali zemeljskega površja. Zaradi številnih področij uporabe podatkov in velike količine podatkov se pojavlja potreba po avtomatskem ločevanju ustreznih točk iz oblaka točk. V nalogi smo obravnavali segmentacijo (ločevanje) objektov v oblaku točk z Gaussovo sfero. Metodo smo uporabili na konkretnem primeru testnih podatkov terestričnega laserskega skeniranja. Opisali smo vse korake od skeniranja testnih podatkov do rezultatov segmentacije. Osredotočili smo se na tri geometrijske oblike objektov, in sicer ravnino, valj in stožec. Opisali smo osnovne lastnosti Houghove transformacije, binarizacije in pretvorbe podatkov v diskretno obliko ter jih vključili v postopek segmentacije. Za izvedbo praktičnega dela naloge smo napisali program za segmentacijo v programskem jeziku Python. Končni rezultat so izrisani oblaki točk treh geometrijskih oblik, ki smo komentirali in ovrednotili. Končne ugotovitve o segmentaciji z Gaussovo sfero so podane v zaključku.

Keywords

geodezija;diplomska naloga;UNI;GIG;oblak točk;segmentacija;Gaussova sfera;Houghova transformacija;

Data

Language:	Slovenian
Year of publishing:	2016
Typology:	2.11 - Undergraduate Thesis
Organization:	UL FGG - Faculty of Civil and Geodetic Engineering
Publisher:	[B. Lipuš]
UDC:	528.8(043.2)
COBISS:	7832929
Views:	2407
Downloads:	603
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Point cloud segmentation using Gaussian sphere
Secondary abstract:	Collecting spatial data using laser scanning is developing quickly. Point clouds, which are primary result of laser scanning, are useful for 3D modelling of scanned objects and Earth's surfaces. Because point clouds are useful in numerous fields and provide a large amount of data, there is a need to automatically extract certain features from point clouds. This thesis describes point cloud segmentation using Gaussian sphere. We used this method on actual terrestrial scanned test data. We described the process in steps from obtaining test data to final results of segmentation. We focused on three geometrical objects, that are plane, cylinder and cone. We also described basic theory about the Hough transform, binarization and changing test data in discrete form, that were used in the process of segmentation. For processing the test data, we wrote a program in Python. With Python and its add-on libraries we plotted intermediate and final results, which we commented and evaluated. Final thoughts about the described segmentation method are given in conclusion.
Secondary keywords:	point cloud;segmentation;Gaussian sphere;Hough transform;
File type:	application/pdf
Type (COBISS):	Bachelor thesis/paper
Thesis comment:	Univ. v Ljubljani, Fak. za gradbeništvo in geodezijo
Pages:	XVI, 21 str., [8] str. pril.
ID:	9175487