PAD: a perceptual application-dependent metric for quality assessment of segmentation algorithms

Detalhes bibliográficos
Autor(a) principal: Sanches, Silvio R. R.
Data de Publicação: 2019
Outros Autores: Sementille, Antonio C. [UNESP], Tori, Romero, Nakamura, Ricardo, Freire, Valdinei
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1007/s11042-019-07958-7
http://hdl.handle.net/11449/194955
Resumo: Extracting elements of interest from video frames is a necessary task in many applications, such as those that require replacing the original background. Quality assessment of foreground extraction algorithms is essential to find the best algorithm for a particular application. This paper presents an application-dependent objective metric capable of evaluating the quality of those algorithms by considering user perception. Our metric identifies types of errors that cause the greatest annoyance based on regions of the scene where users tend to keep their attention during videoconference sessions. We demonstrate the efficiency of our metric by evaluating bilayer segmentation algorithms. The results showed that metric is effective compared to others used to evaluate algorithms for videoconferencing systems.
id UNSP_01694fe49d9de4e47464cc367cbecd5b
oai_identifier_str oai:repositorio.unesp.br:11449/194955
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling PAD: a perceptual application-dependent metric for quality assessment of segmentation algorithmsObjective metricSegmentation qualitySegmentation evaluationVideoconferenceExtracting elements of interest from video frames is a necessary task in many applications, such as those that require replacing the original background. Quality assessment of foreground extraction algorithms is essential to find the best algorithm for a particular application. This paper presents an application-dependent objective metric capable of evaluating the quality of those algorithms by considering user perception. Our metric identifies types of errors that cause the greatest annoyance based on regions of the scene where users tend to keep their attention during videoconference sessions. We demonstrate the efficiency of our metric by evaluating bilayer segmentation algorithms. The results showed that metric is effective compared to others used to evaluate algorithms for videoconferencing systems.Univ Tecnol Fed Parana, Cornelio Procopio, PR, BrazilUniv Estadual Paulista, Bauru, BrazilUniv Sao Paulo, Escola Politecn, Sao Paulo, BrazilUniv Sao Paulo, Sao Paulo, BrazilUniv Estadual Paulista, Bauru, BrazilSpringerUniv Tecnol Fed ParanaUniversidade Estadual Paulista (Unesp)Universidade de São Paulo (USP)Sanches, Silvio R. R.Sementille, Antonio C. [UNESP]Tori, RomeroNakamura, RicardoFreire, Valdinei2020-12-10T16:59:51Z2020-12-10T16:59:51Z2019-11-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article32393-32417http://dx.doi.org/10.1007/s11042-019-07958-7Multimedia Tools And Applications. Dordrecht: Springer, v. 78, n. 22, p. 32393-32417, 2019.1380-7501http://hdl.handle.net/11449/19495510.1007/s11042-019-07958-7WOS:000495400000059Web of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengMultimedia Tools And Applicationsinfo:eu-repo/semantics/openAccess2021-10-23T03:03:18Zoai:repositorio.unesp.br:11449/194955Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T20:27:09.439790Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv PAD: a perceptual application-dependent metric for quality assessment of segmentation algorithms
title PAD: a perceptual application-dependent metric for quality assessment of segmentation algorithms
spellingShingle PAD: a perceptual application-dependent metric for quality assessment of segmentation algorithms
Sanches, Silvio R. R.
Objective metric
Segmentation quality
Segmentation evaluation
Videoconference
title_short PAD: a perceptual application-dependent metric for quality assessment of segmentation algorithms
title_full PAD: a perceptual application-dependent metric for quality assessment of segmentation algorithms
title_fullStr PAD: a perceptual application-dependent metric for quality assessment of segmentation algorithms
title_full_unstemmed PAD: a perceptual application-dependent metric for quality assessment of segmentation algorithms
title_sort PAD: a perceptual application-dependent metric for quality assessment of segmentation algorithms
author Sanches, Silvio R. R.
author_facet Sanches, Silvio R. R.
Sementille, Antonio C. [UNESP]
Tori, Romero
Nakamura, Ricardo
Freire, Valdinei
author_role author
author2 Sementille, Antonio C. [UNESP]
Tori, Romero
Nakamura, Ricardo
Freire, Valdinei
author2_role author
author
author
author
dc.contributor.none.fl_str_mv Univ Tecnol Fed Parana
Universidade Estadual Paulista (Unesp)
Universidade de São Paulo (USP)
dc.contributor.author.fl_str_mv Sanches, Silvio R. R.
Sementille, Antonio C. [UNESP]
Tori, Romero
Nakamura, Ricardo
Freire, Valdinei
dc.subject.por.fl_str_mv Objective metric
Segmentation quality
Segmentation evaluation
Videoconference
topic Objective metric
Segmentation quality
Segmentation evaluation
Videoconference
description Extracting elements of interest from video frames is a necessary task in many applications, such as those that require replacing the original background. Quality assessment of foreground extraction algorithms is essential to find the best algorithm for a particular application. This paper presents an application-dependent objective metric capable of evaluating the quality of those algorithms by considering user perception. Our metric identifies types of errors that cause the greatest annoyance based on regions of the scene where users tend to keep their attention during videoconference sessions. We demonstrate the efficiency of our metric by evaluating bilayer segmentation algorithms. The results showed that metric is effective compared to others used to evaluate algorithms for videoconferencing systems.
publishDate 2019
dc.date.none.fl_str_mv 2019-11-01
2020-12-10T16:59:51Z
2020-12-10T16:59:51Z
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://dx.doi.org/10.1007/s11042-019-07958-7
Multimedia Tools And Applications. Dordrecht: Springer, v. 78, n. 22, p. 32393-32417, 2019.
1380-7501
http://hdl.handle.net/11449/194955
10.1007/s11042-019-07958-7
WOS:000495400000059
url http://dx.doi.org/10.1007/s11042-019-07958-7
http://hdl.handle.net/11449/194955
identifier_str_mv Multimedia Tools And Applications. Dordrecht: Springer, v. 78, n. 22, p. 32393-32417, 2019.
1380-7501
10.1007/s11042-019-07958-7
WOS:000495400000059
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Multimedia Tools And Applications
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 32393-32417
dc.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv Web of Science
reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv
_version_ 1808129203844939776