Download
PDF 6.78 MB
undergraduate thesis
10   7
Segmentation of depth images into planar and cylindrical surfaces using Random Sample Consensus method
Duško Findžanović (2017)
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Computer Engineering and Automation
Chair of Automation and Robotics
Metadata
TitleSegmentacija dubinske slike na ravne i valjkaste površine metodom nasumičnog uzorkovanja
AuthorDuško Findžanović
Mentor(s)Robert Cupec (thesis advisor)
Abstract
Izrađen je program za segmentaciju slike na ravne i valjkaste površine slike pomoću RANSAC metode. Kao ulaz se uzima PCD datoteka koja sadrži parametre slike, a kao rezultat program daje 3D prikaz određene segmentacije slike u obliku oblaka točaka, gdje je svaki segment prikazan drugom bojom. Program je pisan u programskom jeziku C++, te se koristio razvojni alat Microsoft Visual Studio 2013. Također koristile su se funkcije i naredbe iz programske biblioteke PCL (Point Cloud Library). Funkcionalnost programa ispitana je na 20 RGB-D slika
KeywordsPoint Cloud Library segmentation RANSAC C++
Parallel title (English)Segmentation of depth images into planar and cylindrical surfaces using Random Sample Consensus method
Committee MembersRobert Cupec (committee chairperson)
Zdravko Krpić (committee member)
Alfonzo Baumgartner (committee member)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Lower level organizational unitsDepartment of Computer Engineering and Automation
Chair of Automation and Robotics
PlaceOsijek
StateCroatia
Scientific field, discipline, subdisciplineTECHNICAL SCIENCES
Computing
Data Processing
Study programme typeuniversity
Study levelundergraduate
Study programmeUndergraduate University Study Programme in Computer Engineering
Academic title abbreviationuniv.bacc.ing.comp.
Genreundergraduate thesis
Language Croatian
Defense date2017-09-27
Parallel abstract (English)
A program was created for image segmentation into planar and cylindrical surfaces using the RANSAC method is developed. The input to the program is a PCD file and as a result, a 3D visualization of the obtained segmentation is provided, where every segment is depicted with a different color. The program is written in C++ programing language and Microsoft Visual Studio 2013 is used as the main development tool. Furthermore, functions and commands from program library PCL (Point Cloud Library) have also been used. The functionality of the program was tested on 20 RGB-D pictures.
Parallel keywords (Croatian)Point Cloud Library segmentacija RANSAC C++
Resource typetext
Access conditionOpen access
Terms of usehttp://rightsstatements.org/vocab/InC/1.0/
URN:NBNhttps://urn.nsk.hr/urn:nbn:hr:200:287069