izpis_h1_title_alt

Struktura iz gibanja na osnovi homogenih regij
VINOVRŠKI, PATRIK (Author), Kristan, Matej (Mentor) More about this mentor... This link opens in a new window

.pdfPDF - Presentation file, Download (572,75 KB)

Abstract
Pridobivanje strukture iz gibanja zahteva rešitev večih problemov na področju računalniškega vida. Predstavljamo splošen cevovod za gradnjo 3D modelov iz večih kalibriranih slik, kot tudi implementacijo posameznih stopenj. Osnovne stopnje obsegajo pridobivanje značilk, ujemanje značilk, ocena položaja kamer in nazadnje rekonstrukcijo scene. Izbira homogenih regij kot značilk je osnovana na predpostavki, da le te večinoma predstavljajo ravne površine upodobljene scene, kar nam omogoča predstaviti preslikavo regij med slikami s homografijo. Pri iskanju ujemanja značilk je računsko učinkovitejše regije postaviti v normalizirano obliko ter jih predstaviti z vektorskim deskriptorjem. Predstavljena tehnika normalizacije regij omogoča večjo natančnost v stopnjah ujemanja značilk in ocene položaja kamer. Položaj kamer ter strukturo scene pridobimo z novo metodo dekompozicije večih homografij, kar nam omogoča ustvariti rekonstrukcijo upodobljene scene. Predstavljene metode so analizirane z uporabo sintetičnih podatkov.

Language:Slovenian
Keywords:homogene regije, normalizacija regij, homografija, ocena homografije na osnovi regij, dekompozicija homografije, ocena položaja kamere, struktura iz gibanja
Work type:Undergraduate thesis (m5)
Organization:FRI - Faculty of computer and information science
Year:2016
Views:381
Downloads:180
Metadata:XML RDF-CHPDL DC-XML DC-RDF
 
Average score:(0 votes)
Your score:Voting is allowed only to logged in users.
:
Share:AddThis
AddThis uses cookies that require your consent. Edit consent...

Secondary language

Language:English
Title:Structure from motion based on homogeneous regions
Abstract:
Acquiring structure from motion requires a solution to multiple problems in the field of computer vision. We present a general pipeline for the reconstruction of 3D models from multiple calibrated images and the implementation of it's stages. The main stages are feature extraction, feature matching, camera pose estimation and finally scene reconstruction. The selection of homogenous regions as features is based on the assumption that they mostly represent planar surfaces of the imaged scene, which allows us to represent mappings of such regions between images with homographies. In the search for feature matches is computationaly more efficient to transform the regions into a normalized form and represent it with a vector descriptor. The subsequent region normalization technique improves the accuracy in the stages of feature matching and camera pose estimation. A novel method of multiple homography decomposition is used to obtain the camera poses and scene structure allowing us to create a reconstruction of the imaged scene. The presented methods are analyzed using synthetic data.

Keywords:homogenous regions, region normalization, homography, region based homography estimation, homography decomposition, camera pose estimation, structure from motion

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Comments

Leave comment

You have to log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back