Primerjava postopkov 3D rekonstrukcije

diplomsko delo univerzitetnega študijskega programa

Jože Baligač (Author), Božidar Potočnik (Mentor), Peter Podbreznik (Co-mentor)

Abstract

3D rekonstrukcija je več koračni postopek gradnje globinskih modelov iz 2D slik. V diplomskem delu smo predstavili postopek pridobivanja globinskih modelov iz zaporedja več slik. Podrobno smo analizirali fazo projekcijske rekonstrukcije, ki je ena izmed ključnih faz za natančno 3D rekonstrukcijo točk v prostoru. Preučili smo različne metode za izračun projekcijske matrike, in sicer faktorizacijsko metodo, metodo s temeljno matriko in metodo s kalibracijskimi podatki. Predstavili smo sistem, kjer smo omenjene metode implementirali in jih glede na izpeljan evalvacijski kriterij primerjali. Rezultati so pokazali, da je metoda s temeljno matriko najuspešnejša.

Keywords

3D rekonstrukcija;računalniški vid;temeljna matrika;kalibracija;geometrija več pogledov;korespodenčne točke;

Data

Language:	Slovenian
Year of publishing:	2010
Source:	Maribor
Typology:	2.11 - Undergraduate Thesis
Organization:	UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher:	[J. Baligač]
UDC:	004.89/.93(043.2)
COBISS:	14900246
Views:	1989
Downloads:	120
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Comparison of 3D-reconstruction methods
Secondary abstract:	3D-reconstruction is a multi-step method for constructing depth (3D) models from 2D images. In our diploma work, we presented a procedure for acquiring 3D models from a sequence of multiple images. We analyzed in detail a phase for projection reconstruction, which is one of the key steps for accurate 3D-reconstruction of points in space. We studied different methods for projection matrix calculation, namely the factorization method, method with fundamental matrix, and method with calibration data. We presented a system where these methods were implemented and compared according to an evaluation criterion. Results pointed out that the method with fundamental matrix is the most successful.
Secondary keywords:	3D reconstruction;computer vision;fundamental matrix;calibration;multiple view geomatry;corresponding points;
URN:	URN:SI:UM:
Type (COBISS):	Bachelor thesis/paper
Thesis comment:	Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko
Pages:	VII, 32 f.
Keywords (UDC):	science and knowledge;organization;computer science;information;documentation;librarianship;institutions;publications;znanost in znanje;organizacije;informacije;dokumentacija;bibliotekarstvo;institucije;publikacije;prolegomena;fundamentals of knowledge and culture;propaedeutics;prolegomena;splošne osnove znanosti in kulture;computer science and technology;computing;data processing;računalniška znanost in tehnologija;računalništvo;obdelava podatkov;artificial intelligence;umetna inteligenca;
ID:	1003250