3D Surface Reconstruction of Noisy Point Clouds Using Growing Neural Gas: 3D Object/Scene Reconstruction

Please use this identifier to cite or link to this item: http://hdl.handle.net/10045/63397
Información del item - Informació de l'item - Item information
Title: 3D Surface Reconstruction of Noisy Point Clouds Using Growing Neural Gas: 3D Object/Scene Reconstruction
Authors: Orts-Escolano, Sergio | Garcia-Rodriguez, Jose | Morell, Vicente | Cazorla, Miguel | Serra Pérez, José Antonio | Garcia-Garcia, Alberto
Research Group/s: Robótica y Visión Tridimensional (RoViT) | Informática Industrial y Redes de Computadores | UniCAD: Grupo de Investigación en CAD/CAM/CAE de la Universidad de Alicante
Center, Department or Service: Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial | Universidad de Alicante. Departamento de Tecnología Informática y Computación
Keywords: GNG | 3D reconstruction | Low-cost 3D sensor | Scene reconstruction | Object reconstruction
Knowledge Area: Ciencia de la Computación e Inteligencia Artificial | Arquitectura y Tecnología de Computadores
Issue Date: Apr-2016
Publisher: Springer Science+Business Media New York
Citation: Neural Processing Letters. 2016, 43(2): 401-423. doi:10.1007/s11063-015-9421-x
Abstract: With the advent of low-cost 3D sensors and 3D printers, scene and object 3D surface reconstruction has become an important research topic in the last years. In this work, we propose an automatic (unsupervised) method for 3D surface reconstruction from raw unorganized point clouds acquired using low-cost 3D sensors. We have modified the growing neural gas network, which is a suitable model because of its flexibility, rapid adaptation and excellent quality of representation, to perform 3D surface reconstruction of different real-world objects and scenes. Some improvements have been made on the original algorithm considering colour and surface normal information of input data during the learning stage and creating complete triangular meshes instead of basic wire-frame representations. The proposed method is able to successfully create 3D faces online, whereas existing 3D reconstruction methods based on self-organizing maps required post-processing steps to close gaps and holes produced during the 3D reconstruction process. A set of quantitative and qualitative experiments were carried out to validate the proposed method. The method has been implemented and tested on real data, and has been found to be effective at reconstructing noisy point clouds obtained using low-cost 3D sensors.
Sponsor: This work was partially funded by the Spanish Government DPI2013-40534-R Grant.
URI: http://hdl.handle.net/10045/63397
ISSN: 1370-4621 (Print) | 1573-773X (Online)
DOI: 10.1007/s11063-015-9421-x
Language: eng
Type: info:eu-repo/semantics/article
Rights: © Springer Science+Business Media New York 2015. The final publication is available at Springer via http://dx.doi.org/10.1007/s11063-015-9421-x
Peer Review: si
Publisher version: http://dx.doi.org/10.1007/s11063-015-9421-x
Appears in Collections:INV - RoViT - Artículos de Revistas
INV - UNICAD - Artículos de Revistas
INV - I2RC - Artículos de Revistas
INV - AIA - Artículos de Revistas

Files in This Item:
Files in This Item:
File Description SizeFormat 
Thumbnail2016_Orts_etal_NeuralProcessLett_final.pdfVersión final (acceso restringido)4,79 MBAdobe PDFOpen    Request a copy
Thumbnail2016_Orts_etal_NeuralProcessLett_preprint.pdfPreprint (acceso abierto)9,07 MBAdobe PDFOpen Preview

Items in RUA are protected by copyright, with all rights reserved, unless otherwise indicated.