On-line SLAM using clustered landmarks with omnidirectional vision
Autor(a) principal: | |
---|---|
Data de Publicação: | 2010 |
Outros Autores: | |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Journal of the Brazilian Society of Mechanical Sciences and Engineering (Online) |
Texto Completo: | http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1678-58782010000500006 |
Resumo: | The problem of SLAM (simultaneous localization and mapping) is a fundamental problem in autonomous robotics. It arises when a robot must create a map of the regions it has navigated while localizing itself on it, using results from one step to increase precision in another by eliminating errors inherent to the sensors. One common solution consists of establishing landmarks in the environment which are used as reference points for absolute localization estimates and form a sparse map that is iteratively refined as more information is obtained. This paper introduces a method of landmark selection and clustering in omnidirectional images for on-line SLAM, using the SIFT algorithm for initial feature extraction and assuming no prior knowledge of the environment. Visual sensors are an attractive way of collecting information from the environment, but tend to create an excessive amount of landmarks that are individually prone to false matches due to image noise and object similarities. By clustering several features in single objects, our approach eliminates landmarks that do not consistently represent the environment, decreasing computational cost and increasing the reliability of information incorporated. Tests conducted in real navigational situations show a significant improvement in performance without loss of quality. |
id |
ABCM-2_1826dfa7dca49e8931467004aa3cdc6f |
---|---|
oai_identifier_str |
oai:scielo:S1678-58782010000500006 |
network_acronym_str |
ABCM-2 |
network_name_str |
Journal of the Brazilian Society of Mechanical Sciences and Engineering (Online) |
repository_id_str |
|
spelling |
On-line SLAM using clustered landmarks with omnidirectional visionSLAMSIFTomnidirectional visionmobile robot controlThe problem of SLAM (simultaneous localization and mapping) is a fundamental problem in autonomous robotics. It arises when a robot must create a map of the regions it has navigated while localizing itself on it, using results from one step to increase precision in another by eliminating errors inherent to the sensors. One common solution consists of establishing landmarks in the environment which are used as reference points for absolute localization estimates and form a sparse map that is iteratively refined as more information is obtained. This paper introduces a method of landmark selection and clustering in omnidirectional images for on-line SLAM, using the SIFT algorithm for initial feature extraction and assuming no prior knowledge of the environment. Visual sensors are an attractive way of collecting information from the environment, but tend to create an excessive amount of landmarks that are individually prone to false matches due to image noise and object similarities. By clustering several features in single objects, our approach eliminates landmarks that do not consistently represent the environment, decreasing computational cost and increasing the reliability of information incorporated. Tests conducted in real navigational situations show a significant improvement in performance without loss of quality.Associação Brasileira de Engenharia e Ciências Mecânicas - ABCM2010-12-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S1678-58782010000500006Journal of the Brazilian Society of Mechanical Sciences and Engineering v.32 n.spe 2010reponame:Journal of the Brazilian Society of Mechanical Sciences and Engineering (Online)instname:Associação Brasileira de Engenharia e Ciências Mecânicas (ABCM)instacron:ABCM10.1590/S1678-58782010000500006info:eu-repo/semantics/openAccessOkamoto Jr.,JunGuizilini,Vitor Campanholoeng2011-03-11T00:00:00Zoai:scielo:S1678-58782010000500006Revistahttps://www.scielo.br/j/jbsmse/https://old.scielo.br/oai/scielo-oai.php||abcm@abcm.org.br1806-36911678-5878opendoar:2011-03-11T00:00Journal of the Brazilian Society of Mechanical Sciences and Engineering (Online) - Associação Brasileira de Engenharia e Ciências Mecânicas (ABCM)false |
dc.title.none.fl_str_mv |
On-line SLAM using clustered landmarks with omnidirectional vision |
title |
On-line SLAM using clustered landmarks with omnidirectional vision |
spellingShingle |
On-line SLAM using clustered landmarks with omnidirectional vision Okamoto Jr.,Jun SLAM SIFT omnidirectional vision mobile robot control |
title_short |
On-line SLAM using clustered landmarks with omnidirectional vision |
title_full |
On-line SLAM using clustered landmarks with omnidirectional vision |
title_fullStr |
On-line SLAM using clustered landmarks with omnidirectional vision |
title_full_unstemmed |
On-line SLAM using clustered landmarks with omnidirectional vision |
title_sort |
On-line SLAM using clustered landmarks with omnidirectional vision |
author |
Okamoto Jr.,Jun |
author_facet |
Okamoto Jr.,Jun Guizilini,Vitor Campanholo |
author_role |
author |
author2 |
Guizilini,Vitor Campanholo |
author2_role |
author |
dc.contributor.author.fl_str_mv |
Okamoto Jr.,Jun Guizilini,Vitor Campanholo |
dc.subject.por.fl_str_mv |
SLAM SIFT omnidirectional vision mobile robot control |
topic |
SLAM SIFT omnidirectional vision mobile robot control |
description |
The problem of SLAM (simultaneous localization and mapping) is a fundamental problem in autonomous robotics. It arises when a robot must create a map of the regions it has navigated while localizing itself on it, using results from one step to increase precision in another by eliminating errors inherent to the sensors. One common solution consists of establishing landmarks in the environment which are used as reference points for absolute localization estimates and form a sparse map that is iteratively refined as more information is obtained. This paper introduces a method of landmark selection and clustering in omnidirectional images for on-line SLAM, using the SIFT algorithm for initial feature extraction and assuming no prior knowledge of the environment. Visual sensors are an attractive way of collecting information from the environment, but tend to create an excessive amount of landmarks that are individually prone to false matches due to image noise and object similarities. By clustering several features in single objects, our approach eliminates landmarks that do not consistently represent the environment, decreasing computational cost and increasing the reliability of information incorporated. Tests conducted in real navigational situations show a significant improvement in performance without loss of quality. |
publishDate |
2010 |
dc.date.none.fl_str_mv |
2010-12-01 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1678-58782010000500006 |
url |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1678-58782010000500006 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1590/S1678-58782010000500006 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
text/html |
dc.publisher.none.fl_str_mv |
Associação Brasileira de Engenharia e Ciências Mecânicas - ABCM |
publisher.none.fl_str_mv |
Associação Brasileira de Engenharia e Ciências Mecânicas - ABCM |
dc.source.none.fl_str_mv |
Journal of the Brazilian Society of Mechanical Sciences and Engineering v.32 n.spe 2010 reponame:Journal of the Brazilian Society of Mechanical Sciences and Engineering (Online) instname:Associação Brasileira de Engenharia e Ciências Mecânicas (ABCM) instacron:ABCM |
instname_str |
Associação Brasileira de Engenharia e Ciências Mecânicas (ABCM) |
instacron_str |
ABCM |
institution |
ABCM |
reponame_str |
Journal of the Brazilian Society of Mechanical Sciences and Engineering (Online) |
collection |
Journal of the Brazilian Society of Mechanical Sciences and Engineering (Online) |
repository.name.fl_str_mv |
Journal of the Brazilian Society of Mechanical Sciences and Engineering (Online) - Associação Brasileira de Engenharia e Ciências Mecânicas (ABCM) |
repository.mail.fl_str_mv |
||abcm@abcm.org.br |
_version_ |
1754734681846185984 |