Global localization with non-quantized local image features
Autor(a) principal: | |
---|---|
Data de Publicação: | 2012 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.21/5068 |
Resumo: | In the field of appearance-based robot localization, the mainstream approach uses a quantized representation of local image features. An alternative strategy is the exploitation of raw feature descriptors, thus avoiding approximations due to quantization. In this work, the quantized and non-quantized representations are compared with respect to their discriminativity, in the context of the robot global localization problem. Having demonstrated the advantages of the non-quantized representation, the paper proposes mechanisms to reduce the computational burden this approach would carry, when applied in its simplest form. This reduction is achieved through a hierarchical strategy which gradually discards candidate locations and by exploring two simplifying assumptions about the training data. The potential of the non-quantized representation is exploited by resorting to the entropy-discriminativity relation. The idea behind this approach is that the non-quantized representation facilitates the assessment of the distinctiveness of features, through the entropy measure. Building on this finding, the robustness of the localization system is enhanced by modulating the importance of features according to the entropy measure. Experimental results support the effectiveness of this approach, as well as the validity of the proposed computation reduction methods. |
id |
RCAP_a901c9799fb9b9225a1b089068c55344 |
---|---|
oai_identifier_str |
oai:repositorio.ipl.pt:10400.21/5068 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Global localization with non-quantized local image featuresTopological LocalizationAppearance-Based MethodsFeature SelectionInformation ContentEntropyTexture ClassificationOmnidirectional ImagesMarkov LocalizationRobot LocalizationBinary PatternsMobile RobotsRecognitionAppearanceIn the field of appearance-based robot localization, the mainstream approach uses a quantized representation of local image features. An alternative strategy is the exploitation of raw feature descriptors, thus avoiding approximations due to quantization. In this work, the quantized and non-quantized representations are compared with respect to their discriminativity, in the context of the robot global localization problem. Having demonstrated the advantages of the non-quantized representation, the paper proposes mechanisms to reduce the computational burden this approach would carry, when applied in its simplest form. This reduction is achieved through a hierarchical strategy which gradually discards candidate locations and by exploring two simplifying assumptions about the training data. The potential of the non-quantized representation is exploited by resorting to the entropy-discriminativity relation. The idea behind this approach is that the non-quantized representation facilitates the assessment of the distinctiveness of features, through the entropy measure. Building on this finding, the robustness of the localization system is enhanced by modulating the importance of features according to the entropy measure. Experimental results support the effectiveness of this approach, as well as the validity of the proposed computation reduction methods.Elsevier Science BVRCIPLCampos, Francisco M.Correia, LuísCalado, João Manuel Ferreira2015-09-07T09:42:56Z2012-082012-08-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfapplication/pdfhttp://hdl.handle.net/10400.21/5068engCAMPOS, F. M.; CORREIA, L.; CALADO, J. M. F. – Global localization with non-quantized local image features. Robotics and Autonomous Systems. ISSN: 0921-8890. Vol. 60, nr. 8 (2012), pp. 1011-10200921-889010.1016/j.robot.2012.05.015metadata only accessinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-08-03T09:47:57Zoai:repositorio.ipl.pt:10400.21/5068Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T20:14:24.000411Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Global localization with non-quantized local image features |
title |
Global localization with non-quantized local image features |
spellingShingle |
Global localization with non-quantized local image features Campos, Francisco M. Topological Localization Appearance-Based Methods Feature Selection Information Content Entropy Texture Classification Omnidirectional Images Markov Localization Robot Localization Binary Patterns Mobile Robots Recognition Appearance |
title_short |
Global localization with non-quantized local image features |
title_full |
Global localization with non-quantized local image features |
title_fullStr |
Global localization with non-quantized local image features |
title_full_unstemmed |
Global localization with non-quantized local image features |
title_sort |
Global localization with non-quantized local image features |
author |
Campos, Francisco M. |
author_facet |
Campos, Francisco M. Correia, Luís Calado, João Manuel Ferreira |
author_role |
author |
author2 |
Correia, Luís Calado, João Manuel Ferreira |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
RCIPL |
dc.contributor.author.fl_str_mv |
Campos, Francisco M. Correia, Luís Calado, João Manuel Ferreira |
dc.subject.por.fl_str_mv |
Topological Localization Appearance-Based Methods Feature Selection Information Content Entropy Texture Classification Omnidirectional Images Markov Localization Robot Localization Binary Patterns Mobile Robots Recognition Appearance |
topic |
Topological Localization Appearance-Based Methods Feature Selection Information Content Entropy Texture Classification Omnidirectional Images Markov Localization Robot Localization Binary Patterns Mobile Robots Recognition Appearance |
description |
In the field of appearance-based robot localization, the mainstream approach uses a quantized representation of local image features. An alternative strategy is the exploitation of raw feature descriptors, thus avoiding approximations due to quantization. In this work, the quantized and non-quantized representations are compared with respect to their discriminativity, in the context of the robot global localization problem. Having demonstrated the advantages of the non-quantized representation, the paper proposes mechanisms to reduce the computational burden this approach would carry, when applied in its simplest form. This reduction is achieved through a hierarchical strategy which gradually discards candidate locations and by exploring two simplifying assumptions about the training data. The potential of the non-quantized representation is exploited by resorting to the entropy-discriminativity relation. The idea behind this approach is that the non-quantized representation facilitates the assessment of the distinctiveness of features, through the entropy measure. Building on this finding, the robustness of the localization system is enhanced by modulating the importance of features according to the entropy measure. Experimental results support the effectiveness of this approach, as well as the validity of the proposed computation reduction methods. |
publishDate |
2012 |
dc.date.none.fl_str_mv |
2012-08 2012-08-01T00:00:00Z 2015-09-07T09:42:56Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10400.21/5068 |
url |
http://hdl.handle.net/10400.21/5068 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
CAMPOS, F. M.; CORREIA, L.; CALADO, J. M. F. – Global localization with non-quantized local image features. Robotics and Autonomous Systems. ISSN: 0921-8890. Vol. 60, nr. 8 (2012), pp. 1011-1020 0921-8890 10.1016/j.robot.2012.05.015 |
dc.rights.driver.fl_str_mv |
metadata only access info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
metadata only access |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf application/pdf |
dc.publisher.none.fl_str_mv |
Elsevier Science BV |
publisher.none.fl_str_mv |
Elsevier Science BV |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799133401623560192 |