Visual novelty detection with automatic scale selection

Detalhes bibliográficos
Autor(a) principal: Vieira Neto, Hugo
Data de Publicação: 2007
Outros Autores: Nehmzow, Ulrich
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UTFPR (da Universidade Tecnológica Federal do Paraná (RIUT))
Texto Completo: http://repositorio.utfpr.edu.br/jspui/handle/1/647
Resumo: This paper presents experiments with an autonomous inspection robot, whose task was to highlight novel features in its environment from camera images. The experiments used two different attention mechanisms — saliency map and multi-scale Harris detector — and two different novelty detection mechanisms — Grow-When-Required (GWR) neural network and an incremental Principal Component Analysis (PCA). For all mechanisms we compared fixed-scale image encoding with automatically scaled image patches. Results show that automatic scale selection provides a more efficient representation of the visual input space, but that performance is generally better using a fixed-scale image encoding.
id UTFPR-12_154e3719ac4c794a19739c8ea94043de
oai_identifier_str oai:repositorio.utfpr.edu.br:1/647
network_acronym_str UTFPR-12
network_name_str Repositório Institucional da UTFPR (da Universidade Tecnológica Federal do Paraná (RIUT))
repository_id_str
spelling 2013-11-19T15:11:05Z2013-11-19T15:11:05Z2007-05VIEIRA NETO, Hugo; NEHMZOW, Ulrich. Visual novelty detection with automatic scale selection. Robotics and Autonomous Systems, v. 55, n. 9, p. 693-701, maio 2007. Disponível em: <http://dces.essex.ac.uk/staff/udfn/ftp/ras55.pdf>. Acesso em: 15 jul. 2013.0921-8890http://repositorio.utfpr.edu.br/jspui/handle/1/647This paper presents experiments with an autonomous inspection robot, whose task was to highlight novel features in its environment from camera images. The experiments used two different attention mechanisms — saliency map and multi-scale Harris detector — and two different novelty detection mechanisms — Grow-When-Required (GWR) neural network and an incremental Principal Component Analysis (PCA). For all mechanisms we compared fixed-scale image encoding with automatically scaled image patches. Results show that automatic scale selection provides a more efficient representation of the visual input space, but that performance is generally better using a fixed-scale image encoding.engRobotics and Autonomous Systemshttp://dces.essex.ac.uk/staff/udfn/ftp/ras55.pdfO autor pode arquivar a versão preprint. O autor pode arquivar a versão postprint . O autor não pode arquivar a versão/PDF do editor. Disponível em: <http://www.sherpa.ac.uk/romeo/issn/0921-8890/pt/>. Acesso em: 17 jul. 2013.info:eu-repo/semantics/openAccessRobôsRobóticaVisão por computadorRedes neurais (Computação)RobotsRoboticsComputer visionNeural networks (Computer science)Visual novelty detection with automatic scale selectioninfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleCuritibaVieira Neto, HugoNehmzow, Ulrichreponame:Repositório Institucional da UTFPR (da Universidade Tecnológica Federal do Paraná (RIUT))instname:Universidade Tecnológica Federal do Paraná (UTFPR)instacron:UTFPRTHUMBNAILROBOT. AUTON. SYST._Vieira Neto, Hugo_2007.pdf.jpgROBOT. AUTON. SYST._Vieira Neto, Hugo_2007.pdf.jpgGenerated Thumbnailimage/jpeg1426http://repositorio.utfpr.edu.br:8080/jspui/bitstream/1/647/4/ROBOT.%20AUTON.%20SYST._Vieira%20Neto%2c%20Hugo_2007.pdf.jpg2be05e882a5adab8178055779f17ba0aMD54ORIGINALROBOT. AUTON. SYST._Vieira Neto, Hugo_2007.pdfROBOT. AUTON. SYST._Vieira Neto, Hugo_2007.pdfapplication/pdf667739http://repositorio.utfpr.edu.br:8080/jspui/bitstream/1/647/1/ROBOT.%20AUTON.%20SYST._Vieira%20Neto%2c%20Hugo_2007.pdf092b756388b2a389fa00bbc251cfc1cdMD51LICENSElicense.txtlicense.txttext/plain; charset=utf-81220http://repositorio.utfpr.edu.br:8080/jspui/bitstream/1/647/2/license.txt3cbdb04c3d289deb9dca129a3870a6e1MD52TEXTROBOT. AUTON. SYST._Vieira Neto, Hugo_2007.pdf.txtROBOT. AUTON. SYST._Vieira Neto, Hugo_2007.pdf.txtExtracted texttext/plain38543http://repositorio.utfpr.edu.br:8080/jspui/bitstream/1/647/3/ROBOT.%20AUTON.%20SYST._Vieira%20Neto%2c%20Hugo_2007.pdf.txt26d365ed49c43a7fcfc611fc23860693MD531/6472015-03-07 03:12:26.255oai:repositorio.utfpr.edu.br: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Repositório de PublicaçõesPUBhttp://repositorio.utfpr.edu.br:8080/oai/requestopendoar:2015-03-07T06:12:26Repositório Institucional da UTFPR (da Universidade Tecnológica Federal do Paraná (RIUT)) - Universidade Tecnológica Federal do Paraná (UTFPR)false
dc.title.pt_BR.fl_str_mv Visual novelty detection with automatic scale selection
title Visual novelty detection with automatic scale selection
spellingShingle Visual novelty detection with automatic scale selection
Vieira Neto, Hugo
Robôs
Robótica
Visão por computador
Redes neurais (Computação)
Robots
Robotics
Computer vision
Neural networks (Computer science)
title_short Visual novelty detection with automatic scale selection
title_full Visual novelty detection with automatic scale selection
title_fullStr Visual novelty detection with automatic scale selection
title_full_unstemmed Visual novelty detection with automatic scale selection
title_sort Visual novelty detection with automatic scale selection
author Vieira Neto, Hugo
author_facet Vieira Neto, Hugo
Nehmzow, Ulrich
author_role author
author2 Nehmzow, Ulrich
author2_role author
dc.contributor.author.fl_str_mv Vieira Neto, Hugo
Nehmzow, Ulrich
dc.subject.por.fl_str_mv Robôs
Robótica
Visão por computador
Redes neurais (Computação)
Robots
Robotics
Computer vision
Neural networks (Computer science)
topic Robôs
Robótica
Visão por computador
Redes neurais (Computação)
Robots
Robotics
Computer vision
Neural networks (Computer science)
description This paper presents experiments with an autonomous inspection robot, whose task was to highlight novel features in its environment from camera images. The experiments used two different attention mechanisms — saliency map and multi-scale Harris detector — and two different novelty detection mechanisms — Grow-When-Required (GWR) neural network and an incremental Principal Component Analysis (PCA). For all mechanisms we compared fixed-scale image encoding with automatically scaled image patches. Results show that automatic scale selection provides a more efficient representation of the visual input space, but that performance is generally better using a fixed-scale image encoding.
publishDate 2007
dc.date.issued.fl_str_mv 2007-05
dc.date.accessioned.fl_str_mv 2013-11-19T15:11:05Z
dc.date.available.fl_str_mv 2013-11-19T15:11:05Z
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.citation.fl_str_mv VIEIRA NETO, Hugo; NEHMZOW, Ulrich. Visual novelty detection with automatic scale selection. Robotics and Autonomous Systems, v. 55, n. 9, p. 693-701, maio 2007. Disponível em: <http://dces.essex.ac.uk/staff/udfn/ftp/ras55.pdf>. Acesso em: 15 jul. 2013.
dc.identifier.uri.fl_str_mv http://repositorio.utfpr.edu.br/jspui/handle/1/647
dc.identifier.issn.none.fl_str_mv 0921-8890
identifier_str_mv VIEIRA NETO, Hugo; NEHMZOW, Ulrich. Visual novelty detection with automatic scale selection. Robotics and Autonomous Systems, v. 55, n. 9, p. 693-701, maio 2007. Disponível em: <http://dces.essex.ac.uk/staff/udfn/ftp/ras55.pdf>. Acesso em: 15 jul. 2013.
0921-8890
url http://repositorio.utfpr.edu.br/jspui/handle/1/647
dc.language.iso.fl_str_mv eng
language eng
dc.relation.ispartof.pt_BR.fl_str_mv Robotics and Autonomous Systems
dc.relation.uri.pt_BR.fl_str_mv http://dces.essex.ac.uk/staff/udfn/ftp/ras55.pdf
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Curitiba
publisher.none.fl_str_mv Curitiba
dc.source.none.fl_str_mv reponame:Repositório Institucional da UTFPR (da Universidade Tecnológica Federal do Paraná (RIUT))
instname:Universidade Tecnológica Federal do Paraná (UTFPR)
instacron:UTFPR
instname_str Universidade Tecnológica Federal do Paraná (UTFPR)
instacron_str UTFPR
institution UTFPR
reponame_str Repositório Institucional da UTFPR (da Universidade Tecnológica Federal do Paraná (RIUT))
collection Repositório Institucional da UTFPR (da Universidade Tecnológica Federal do Paraná (RIUT))
bitstream.url.fl_str_mv http://repositorio.utfpr.edu.br:8080/jspui/bitstream/1/647/4/ROBOT.%20AUTON.%20SYST._Vieira%20Neto%2c%20Hugo_2007.pdf.jpg
http://repositorio.utfpr.edu.br:8080/jspui/bitstream/1/647/1/ROBOT.%20AUTON.%20SYST._Vieira%20Neto%2c%20Hugo_2007.pdf
http://repositorio.utfpr.edu.br:8080/jspui/bitstream/1/647/2/license.txt
http://repositorio.utfpr.edu.br:8080/jspui/bitstream/1/647/3/ROBOT.%20AUTON.%20SYST._Vieira%20Neto%2c%20Hugo_2007.pdf.txt
bitstream.checksum.fl_str_mv 2be05e882a5adab8178055779f17ba0a
092b756388b2a389fa00bbc251cfc1cd
3cbdb04c3d289deb9dca129a3870a6e1
26d365ed49c43a7fcfc611fc23860693
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
repository.name.fl_str_mv Repositório Institucional da UTFPR (da Universidade Tecnológica Federal do Paraná (RIUT)) - Universidade Tecnológica Federal do Paraná (UTFPR)
repository.mail.fl_str_mv
_version_ 1805923178781868032