Object recognition in noisy RGB-D data using GNG

Please use this identifier to cite or link to this item: http://hdl.handle.net/10045/70688
Información del item - Informació de l'item - Item information
Title: Object recognition in noisy RGB-D data using GNG
Authors: Rangel, José Carlos | Morell, Vicente | Cazorla, Miguel | Orts-Escolano, Sergio | Garcia-Rodriguez, Jose
Research Group/s: Robótica y Visión Tridimensional (RoViT) | Informática Industrial y Redes de Computadores
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 | Universidad de Alicante. Instituto Universitario de Investigación Informática
Keywords: 3D object recognition | Growing neural gas | Keypoint detection
Knowledge Area: Ciencia de la Computación e Inteligencia Artificial | Arquitectura y Tecnología de Computadores
Issue Date: Nov-2017
Publisher: Springer London
Citation: Pattern Analysis and Applications. 2017, 20(4): 1061-1076. doi:10.1007/s10044-016-0546-y
Abstract: Object recognition in 3D scenes is a research field in which there is intense activity guided by the problems related to the use of 3D point clouds. Some of these problems are influenced by the presence of noise in the cloud that reduces the effectiveness of a recognition process. This work proposes a method for dealing with the noise present in point clouds by applying the growing neural gas (GNG) network filtering algorithm. This method is able to represent the input data with the desired number of neurons while preserving the topology of the input space. The GNG obtained results which were compared with a Voxel grid filter to determine the efficacy of our approach. Moreover, since a stage of the recognition process includes the detection of keypoints in a cloud, we evaluated different keypoint detectors to determine which one produces the best results in the selected pipeline. Experiments show how the GNG method yields better recognition results than other filtering algorithms when noise is present.
URI: http://hdl.handle.net/10045/70688
ISSN: 1433-7541 (Print) | 1433-755X (Online)
DOI: 10.1007/s10044-016-0546-y
Language: eng
Type: info:eu-repo/semantics/article
Rights: © Springer-Verlag London 2016
Peer Review: si
Publisher version: http://dx.doi.org/10.1007/s10044-016-0546-y
Appears in Collections:INV - I2RC - Artículos de Revistas
INV - RoViT - Artículos de Revistas
INV - AIA - Artículos de Revistas

Files in This Item:
Files in This Item:
File Description SizeFormat 
Thumbnail2017_Rangel_etal_PatternAnalApplic_final.pdfVersión final (acceso restringido)2,84 MBAdobe PDFOpen    Request a copy
Thumbnail2017_Rangel_etal_PatternAnalApplic_preprint.pdfPreprint (acceso abierto)4,01 MBAdobe PDFOpen Preview

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