Novelty detection and segmentation based on Gaussian mixture models: a case study in 3D robotic laser mapping
Autor(a) principal: | |
---|---|
Data de Publicação: | 2013 |
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/10316/27416 https://doi.org/10.1016/j.robot.2013.06.004 |
Resumo: | This article proposes a framework to detect and segment changes in robotics datasets, using 3D robotic mapping as a case study. The problem is very relevant in several application domains, not necessarily related with mobile robotics, including security, health, industry and military applications. The aim is to identify significant changes by comparing current data with previous data provided by sensors. This feature is extremely challenging because large amounts of noisy data must be processed in a feasible way. The proposed framework deals with novelty detection and segmentation in robotic maps using clusters provided by Gaussian Mixture Models (GMMs). GMMs provides a feature space that enables data compression and effective processing. Two alternative criteria to detect changes in the GMM space are compared: a greedy technique based on the Earth Mover’s Distance (EMD); and a structural matching algorithm that fulfills both absolute (global matching) and relative constraints (structural matching). The proposed framework is evaluated with real robotic datasets and compared with other methods known from literature. With this purpose, 3D mapping experiments are carried out with both simulated data and real data from a mobile robot equipped with a 3D range sensor. |
id |
RCAP_1061f603e9845a67261cc904a4506d23 |
---|---|
oai_identifier_str |
oai:estudogeral.uc.pt:10316/27416 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Novelty detection and segmentation based on Gaussian mixture models: a case study in 3D robotic laser mappingNovelty detectionGaussian mixture model3D robotic mappingThis article proposes a framework to detect and segment changes in robotics datasets, using 3D robotic mapping as a case study. The problem is very relevant in several application domains, not necessarily related with mobile robotics, including security, health, industry and military applications. The aim is to identify significant changes by comparing current data with previous data provided by sensors. This feature is extremely challenging because large amounts of noisy data must be processed in a feasible way. The proposed framework deals with novelty detection and segmentation in robotic maps using clusters provided by Gaussian Mixture Models (GMMs). GMMs provides a feature space that enables data compression and effective processing. Two alternative criteria to detect changes in the GMM space are compared: a greedy technique based on the Earth Mover’s Distance (EMD); and a structural matching algorithm that fulfills both absolute (global matching) and relative constraints (structural matching). The proposed framework is evaluated with real robotic datasets and compared with other methods known from literature. With this purpose, 3D mapping experiments are carried out with both simulated data and real data from a mobile robot equipped with a 3D range sensor.Elsevier2013-12info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://hdl.handle.net/10316/27416http://hdl.handle.net/10316/27416https://doi.org/10.1016/j.robot.2013.06.004engDREWS-JR., Paulo [et. al] - Novelty detection and segmentation based on Gaussian mixture models: a case study in 3D robotic laser mapping. "Robotics and Autonomous Systems". ISSN 0921-8890. Vol. 61 Nº. 12 (2013) p. 1696-17090921-8890http://www.sciencedirect.com/science/article/pii/S0921889013001115Drews-Jr., PauloNúñez, PedroRocha, Rui P.Campos, MarioDias, Jorgeinfo: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:RCAAP2020-01-29T14:49:52Zoai:estudogeral.uc.pt:10316/27416Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T20:57:55.542605Repositório 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 |
Novelty detection and segmentation based on Gaussian mixture models: a case study in 3D robotic laser mapping |
title |
Novelty detection and segmentation based on Gaussian mixture models: a case study in 3D robotic laser mapping |
spellingShingle |
Novelty detection and segmentation based on Gaussian mixture models: a case study in 3D robotic laser mapping Drews-Jr., Paulo Novelty detection Gaussian mixture model 3D robotic mapping |
title_short |
Novelty detection and segmentation based on Gaussian mixture models: a case study in 3D robotic laser mapping |
title_full |
Novelty detection and segmentation based on Gaussian mixture models: a case study in 3D robotic laser mapping |
title_fullStr |
Novelty detection and segmentation based on Gaussian mixture models: a case study in 3D robotic laser mapping |
title_full_unstemmed |
Novelty detection and segmentation based on Gaussian mixture models: a case study in 3D robotic laser mapping |
title_sort |
Novelty detection and segmentation based on Gaussian mixture models: a case study in 3D robotic laser mapping |
author |
Drews-Jr., Paulo |
author_facet |
Drews-Jr., Paulo Núñez, Pedro Rocha, Rui P. Campos, Mario Dias, Jorge |
author_role |
author |
author2 |
Núñez, Pedro Rocha, Rui P. Campos, Mario Dias, Jorge |
author2_role |
author author author author |
dc.contributor.author.fl_str_mv |
Drews-Jr., Paulo Núñez, Pedro Rocha, Rui P. Campos, Mario Dias, Jorge |
dc.subject.por.fl_str_mv |
Novelty detection Gaussian mixture model 3D robotic mapping |
topic |
Novelty detection Gaussian mixture model 3D robotic mapping |
description |
This article proposes a framework to detect and segment changes in robotics datasets, using 3D robotic mapping as a case study. The problem is very relevant in several application domains, not necessarily related with mobile robotics, including security, health, industry and military applications. The aim is to identify significant changes by comparing current data with previous data provided by sensors. This feature is extremely challenging because large amounts of noisy data must be processed in a feasible way. The proposed framework deals with novelty detection and segmentation in robotic maps using clusters provided by Gaussian Mixture Models (GMMs). GMMs provides a feature space that enables data compression and effective processing. Two alternative criteria to detect changes in the GMM space are compared: a greedy technique based on the Earth Mover’s Distance (EMD); and a structural matching algorithm that fulfills both absolute (global matching) and relative constraints (structural matching). The proposed framework is evaluated with real robotic datasets and compared with other methods known from literature. With this purpose, 3D mapping experiments are carried out with both simulated data and real data from a mobile robot equipped with a 3D range sensor. |
publishDate |
2013 |
dc.date.none.fl_str_mv |
2013-12 |
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/10316/27416 http://hdl.handle.net/10316/27416 https://doi.org/10.1016/j.robot.2013.06.004 |
url |
http://hdl.handle.net/10316/27416 https://doi.org/10.1016/j.robot.2013.06.004 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
DREWS-JR., Paulo [et. al] - Novelty detection and segmentation based on Gaussian mixture models: a case study in 3D robotic laser mapping. "Robotics and Autonomous Systems". ISSN 0921-8890. Vol. 61 Nº. 12 (2013) p. 1696-1709 0921-8890 http://www.sciencedirect.com/science/article/pii/S0921889013001115 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Elsevier |
publisher.none.fl_str_mv |
Elsevier |
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_ |
1799133869339836416 |