| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

# Show document

Title: Algoritmi odstranjevanja osirotelih točk iz oblaka 3D točk : diplomsko delo Gornik, Aljaž (Author)Lipuš, Bogdan (Mentor) More about this mentor... UN_Gornik_Aljaz_2021.pdf (6,04 MB)MD5: 41FC6B3DBE155EB2136FD536741DD77B Slovenian Bachelor thesis/paper (mb11) 2.11 - Undergraduate Thesis FERI - Faculty of Electrical Engineering and Computer Science Diplomsko delo obsega študijo algoritmov, ki odstranjujejo osirotele točke, ter njihovo primerjavo. V nadaljevanju bomo predstavili osnove pojme, ki so potrebni za razumevanje našega diplomskega dela. Po predstavitvi pojmov bomo podrobno spoznali teoretično ozadje, delovanje, vključene algoritme in implementacijo metode kvartilnega razmika, statističnega filtra, filtriranja s polmerom, pogojnega filtra, ter filtriranja z mnogotero razdaljo in aproksimacijo normale. Implementirane metode testiramo nad različnimi oblaki 3D točk, z različnimi parametri in prikažemo rezultate. Analiza rezultatov kaže, da je na splošno najbolj uporaben statistični filter. algoritem, točke, osirotele točke, odstranjevanje osirotelih točk, 3D oblak točk 2021 Maribor [A. Gornik] XI, 63 f. Maribor 004.9.021(043.2) 88080131 109 50 KTFMB - FERI

Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

## Licences

License: CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes. 04.08.2021

## Secondary language

Language: English Algorithms for outliers removal from 3D point clouds In our thesis we conduct a study and comparison of algorithms for outliers removal. Firstly we present the basic concepts needed for understanding the thesis. After presenting the concepts, we explain the theoretical background, operations, involved algorithms and implementation of the interquartile range method, statistical filter, radius filtering, conditional filter, and filtering with manifold distance and normal estimation. We test the implemented methods on multiple 3D point clouds with different parameter settings and display the filtered results. The resulting analysis shows, that the best filtering method is statistical filter. algorithm, points, outliers, outlier removal, 3D point cloud