Imagen de Portada

Object recognition in noisy RGB-D data using GNG

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...

Descripción completa

Autores Principales: Rangel, José Carlos, Morell, Vicente, Cazorla, Miguel, Orts-Escolano, Sergio, García-Rodríguez, José
Formato: Artículo
Idioma: Inglés
Publicado: Pattern Analysis and Applications 2019
Materias:
3D object recognition
Growing neural gas
Keypoint detection
Acceso en línea: https://link.springer.com/article/10.1007/s10044-016-0546-y
https://doi.org/10.1007/s10044-016-0546-y
http://ridda2.utp.ac.pa/handle/123456789/6475
http://ridda2.utp.ac.pa/handle/123456789/6475
id RepoUTP6475
recordtype dspace
spelling RepoUTP64752021-07-06T15:35:10Z Object recognition in noisy RGB-D data using GNG Rangel, José Carlos Morell, Vicente Cazorla, Miguel Orts-Escolano, Sergio García-Rodríguez, José 3D object recognition Growing neural gas Keypoint detection 3D object recognition Growing neural gas Keypoint detection 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. 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. 2019-08-30T16:10:28Z 2019-08-30T16:10:28Z 2019-08-30T16:10:28Z 2019-08-30T16:10:28Z 04/26/2016 04/26/2016 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion https://link.springer.com/article/10.1007/s10044-016-0546-y https://doi.org/10.1007/s10044-016-0546-y http://ridda2.utp.ac.pa/handle/123456789/6475 http://ridda2.utp.ac.pa/handle/123456789/6475 eng info:eu-repo/semantics/embargoedAccess application/pdf text/html Pattern Analysis and Applications Pattern Analysis and Applications
institution Universidad Tecnológica de Panamá
collection Repositorio UTP – Ridda2
language Inglés
topic 3D object recognition
Growing neural gas
Keypoint detection
3D object recognition
Growing neural gas
Keypoint detection
spellingShingle 3D object recognition
Growing neural gas
Keypoint detection
3D object recognition
Growing neural gas
Keypoint detection
Rangel, José Carlos
Morell, Vicente
Cazorla, Miguel
Orts-Escolano, Sergio
García-Rodríguez, José
Object recognition in noisy RGB-D data using GNG
description 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.
format Artículo
author Rangel, José Carlos
Morell, Vicente
Cazorla, Miguel
Orts-Escolano, Sergio
García-Rodríguez, José
author_sort Rangel, José Carlos
title Object recognition in noisy RGB-D data using GNG
title_short Object recognition in noisy RGB-D data using GNG
title_full Object recognition in noisy RGB-D data using GNG
title_fullStr Object recognition in noisy RGB-D data using GNG
title_full_unstemmed Object recognition in noisy RGB-D data using GNG
title_sort object recognition in noisy rgb-d data using gng
publisher Pattern Analysis and Applications
publishDate 2019
url https://link.springer.com/article/10.1007/s10044-016-0546-y
https://doi.org/10.1007/s10044-016-0546-y
http://ridda2.utp.ac.pa/handle/123456789/6475
http://ridda2.utp.ac.pa/handle/123456789/6475
_version_ 1796209558079668224
score 12.040815

Ejemplares similares