Napredna pretraga

Pregled bibliografske jedinice broj: 623834

An Efficient Method for Surface Registration


Pribanić, Tomislav; Diez, Yago; Sergio Fernandez, Sergio; Salvi, Joaquim
An Efficient Method for Surface Registration // Proceedings of the International Conference on Computer Vision Theory and Applications, VISIGRAPP 2013 / Braz, Jose ; Battiato, Sebastiano (ur.).
Barcelona: SCITEPRESS – Science and Technology Publications, 2013. str. 500-503 (poster, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


Naslov
An Efficient Method for Surface Registration

Autori
Pribanić, Tomislav ; Diez, Yago ; Sergio Fernandez, Sergio ; Salvi, Joaquim

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the International Conference on Computer Vision Theory and Applications, VISIGRAPP 2013 / Braz, Jose ; Battiato, Sebastiano - Barcelona : SCITEPRESS – Science and Technology Publications, 2013, 500-503

ISBN
978-989-8565-47-1

Skup
International Conference on Computer Vision Theory and Applications, VISIGRAPP 2013

Mjesto i datum
Barcelona, Španjolska, 21-24.02.2013

Vrsta sudjelovanja
Poster

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Surface Registration; 3D reconstruction; inertial sensor

Sažetak
3D object data acquired from different viewpoints are usually expressed in different spatial coordinate systems where systems’ spatial relations are defined by Euclidean transformation parameters: three rotation angles and a translation vector. The computation of those Euclidean parameters is a task of surface registration. In a nutshell all registration methods revolve around two goals: first how to extract the most reliable features for correspondence search between views in order to come up with the set of candidate solutions, secondly how to quickly pinpoint the best, i.e. satisfying, solution. Occasionally some registration method expects also other data, e.g. normal vectors, to be provided besides 3D position data. However, no method assumed the possibility that part of Euclidean parameters could be reliably known in advance. Acknowledging technology advancements we argue that it become relatively convenient to include in 3D reconstruction system some inertial sensor which readily provides info about data orientation. Assuming that such data is provided, we demonstrate a simple, but yet time efficient and accurate registration method.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo



POVEZANOST RADA


Projekt / tema
036-0362979-1554 - Neinvazivna mjerenja i postupci u biomedicini (Stanko Tonković, )

Ustanove
Fakultet elektrotehnike i računarstva, Zagreb

Autor s matičnim brojem:
Tomislav Pribanić, (223415)