3D model reconstruction using neural gas accelerated on GPU
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10045/53499
Title: | 3D model reconstruction using neural gas accelerated on GPU |
---|---|
Authors: | Orts-Escolano, Sergio | Garcia-Rodriguez, Jose | Serra Pérez, José Antonio | Jimeno-Morenilla, Antonio | Garcia-Garcia, Alberto | Morell, Vicente | Cazorla, Miguel |
Research Group/s: | Informática Industrial y Redes de Computadores | UniCAD: Grupo de Investigación en CAD/CAM/CAE de la Universidad de Alicante | Robótica y Visión Tridimensional (RoViT) |
Center, Department or Service: | Universidad de Alicante. Departamento de Tecnología Informática y Computación | Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial |
Keywords: | Neural gas | Topology preservation | 3D model reconstruction | Graphics Processing Units |
Knowledge Area: | Arquitectura y Tecnología de Computadores | Ciencia de la Computación e Inteligencia Artificial |
Issue Date: | Jul-2015 |
Publisher: | Elsevier |
Citation: | Applied Soft Computing. 2015, 32: 87-100. doi:10.1016/j.asoc.2015.03.042 |
Abstract: | In this work, we propose the use of the neural gas (NG), a neural network that uses an unsupervised Competitive Hebbian Learning (CHL) rule, to develop a reverse engineering process. This is a simple and accurate method to reconstruct objects from point clouds obtained from multiple overlapping views using low-cost sensors. In contrast to other methods that may need several stages that include downsampling, noise filtering and many other tasks, the NG automatically obtains the 3D model of the scanned objects. To demonstrate the validity of our proposal we tested our method with several models and performed a study of the neural network parameterization computing the quality of representation and also comparing results with other neural methods like growing neural gas and Kohonen maps or classical methods like Voxel Grid. We also reconstructed models acquired by low cost sensors that can be used in virtual and augmented reality environments for redesign or manipulation purposes. Since the NG algorithm has a strong computational cost we propose its acceleration. We have redesigned and implemented the NG learning algorithm to fit it onto Graphics Processing Units using CUDA. A speed-up of 180× faster is obtained compared to the sequential CPU version. |
Sponsor: | This work was partially funded by the Spanish Government DPI2013-40534-R grant. |
URI: | http://hdl.handle.net/10045/53499 |
ISSN: | 1568-4946 (Print) | 1872-9681 (Online) |
DOI: | 10.1016/j.asoc.2015.03.042 |
Language: | eng |
Type: | info:eu-repo/semantics/article |
Rights: | © 2015 Elsevier B.V. |
Peer Review: | si |
Publisher version: | http://dx.doi.org/10.1016/j.asoc.2015.03.042 |
Appears in Collections: | INV - I2RC - Artículos de Revistas INV - UNICAD - Artículos de Revistas INV - RoViT - Artículos de Revistas INV - AIA - Artículos de Revistas |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
2015_Orts_etal_ApplSoftComp_final.pdf | Versión final (acceso restringido) | 3,92 MB | Adobe PDF | Open Request a copy |
2015_Orts_etal_ApplSoftComp_preprint.pdf | Preprint (acceso abierto) | 7,7 MB | Adobe PDF | Open Preview |
Items in RUA are protected by copyright, with all rights reserved, unless otherwise indicated.