LexToMap: lexical-based topological mapping

Any robot should be provided with a proper representation of its environment in order to perform navigation and other tasks. In addition to metrical approaches, topological mapping generates graph representations in which nodes and edges correspond to locations and transitions. In this article, we p...

Full description

Saved in:
Bibliographic Details
Main Author: Rangel, José Carlos (author)
Other Authors: Martínez Gómez, Jesus (author), García Varea, Ismael (author), Cazorla, Miguel (author)
Format: article
Language:English
Published: 2019
Subjects:
Online Access:https://www.tandfonline.com/doi/abs/10.1080/01691864.2016.1261045
https://ridda2.utp.ac.pa/handle/123456789/9434
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1869652477741105152
author Rangel, José Carlos
author2 Martínez Gómez, Jesus
García Varea, Ismael
Cazorla, Miguel
author2_role author
author
author
author_browse Cazorla, Miguel
García Varea, Ismael
Martínez Gómez, Jesus
Rangel, José Carlos
author_facet Rangel, José Carlos
Martínez Gómez, Jesus
García Varea, Ismael
Cazorla, Miguel
author_role author
collection Repositorio Institucional de documento digitales de acceso abierto de la UTP
dc.creator.none.fl_str_mv Rangel, José Carlos
Martínez Gómez, Jesus
García Varea, Ismael
Cazorla, Miguel
dc.date.none.fl_str_mv 11/30/2016
11/30/2016
2019-12-17T19:33:42Z
2019-12-17T19:33:42Z
2019-12-17T19:33:42Z
2019-12-17T19:33:42Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv https://www.tandfonline.com/doi/abs/10.1080/01691864.2016.1261045
https://ridda2.utp.ac.pa/handle/123456789/9434
https://ridda2.utp.ac.pa/handle/123456789/9434
dc.language.none.fl_str_mv eng
eng
dc.rights.none.fl_str_mv info:eu-repo/semantics/embargoedAccess
dc.source.none.fl_str_mv reponame:Repositorio Institucional de documento digitales de acceso abierto de la UTP
instname:Universidad Tecnológica de Panamá
instacron:U Tecnológica de Panamá
dc.subject.none.fl_str_mv Topological mapping
deep learning
localization
image annotations
lexical labels
Topological mapping
deep learning
localization
image annotations
lexical labels
dc.title.none.fl_str_mv LexToMap: lexical-based topological mapping
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
description Any robot should be provided with a proper representation of its environment in order to perform navigation and other tasks. In addition to metrical approaches, topological mapping generates graph representations in which nodes and edges correspond to locations and transitions. In this article, we present LexToMap, a topological mapping procedure that relies on image annotations. These annotations, represented in this work by lexical labels, are obtained from pre-trained deep learning models, namely CNNs, and are used to estimate image similarities. Moreover, the lexical labels contribute to the descriptive capabilities of the topological maps. The proposal has been evaluated using the KTH-IDOL 2 data-set, which consists of image sequences acquired within an indoor environment under three different lighting conditions. The generality of the procedure as well as the descriptive capabilities of the generated maps validate the proposal.
eu_rights_str_mv embargoedAccess
format article
id lrtest_fafb9d2d6607924e27af981bc8e9cd2d
instacron_str U Tecnológica de Panamá
institution U Tecnológica de Panamá
instname_str Universidad Tecnológica de Panamá
language eng
network_acronym_str lrtest
network_name_str lr
oai_identifier_str oai:ridda2.utp.ac.pa:123456789/9434
publishDate 2019
publishDateSort 2019
reponame_str Repositorio Institucional de documento digitales de acceso abierto de la UTP
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling LexToMap: lexical-based topological mappingRangel, José CarlosMartínez Gómez, JesusGarcía Varea, IsmaelCazorla, MiguelTopological mappingdeep learninglocalizationimage annotationslexical labelsTopological mappingdeep learninglocalizationimage annotationslexical labelsAny robot should be provided with a proper representation of its environment in order to perform navigation and other tasks. In addition to metrical approaches, topological mapping generates graph representations in which nodes and edges correspond to locations and transitions. In this article, we present LexToMap, a topological mapping procedure that relies on image annotations. These annotations, represented in this work by lexical labels, are obtained from pre-trained deep learning models, namely CNNs, and are used to estimate image similarities. Moreover, the lexical labels contribute to the descriptive capabilities of the topological maps. The proposal has been evaluated using the KTH-IDOL 2 data-set, which consists of image sequences acquired within an indoor environment under three different lighting conditions. The generality of the procedure as well as the descriptive capabilities of the generated maps validate the proposal.Any robot should be provided with a proper representation of its environment in order to perform navigation and other tasks. In addition to metrical approaches, topological mapping generates graph representations in which nodes and edges correspond to locations and transitions. In this article, we present LexToMap, a topological mapping procedure that relies on image annotations. These annotations, represented in this work by lexical labels, are obtained from pre-trained deep learning models, namely CNNs, and are used to estimate image similarities. Moreover, the lexical labels contribute to the descriptive capabilities of the topological maps. The proposal has been evaluated using the KTH-IDOL 2 data-set, which consists of image sequences acquired within an indoor environment under three different lighting conditions. The generality of the procedure as well as the descriptive capabilities of the generated maps validate the proposal.2019-12-17T19:33:42Z2019-12-17T19:33:42Z2019-12-17T19:33:42Z2019-12-17T19:33:42Z11/30/201611/30/2016info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://www.tandfonline.com/doi/abs/10.1080/01691864.2016.1261045https://ridda2.utp.ac.pa/handle/123456789/9434https://ridda2.utp.ac.pa/handle/123456789/9434engenginfo:eu-repo/semantics/embargoedAccessreponame:Repositorio Institucional de documento digitales de acceso abierto de la UTPinstname:Universidad Tecnológica de Panamáinstacron:U Tecnológica de Panamáoai:ridda2.utp.ac.pa:123456789/94342021-07-06T15:35:10Z
spellingShingle LexToMap: lexical-based topological mapping
Rangel, José Carlos
Topological mapping
deep learning
localization
image annotations
lexical labels
Topological mapping
deep learning
localization
image annotations
lexical labels
status_str publishedVersion
title LexToMap: lexical-based topological mapping
title_full LexToMap: lexical-based topological mapping
title_fullStr LexToMap: lexical-based topological mapping
title_full_unstemmed LexToMap: lexical-based topological mapping
title_short LexToMap: lexical-based topological mapping
title_sort LexToMap: lexical-based topological mapping
topic Topological mapping
deep learning
localization
image annotations
lexical labels
Topological mapping
deep learning
localization
image annotations
lexical labels
url https://www.tandfonline.com/doi/abs/10.1080/01691864.2016.1261045
https://ridda2.utp.ac.pa/handle/123456789/9434