Human action recognition using 2D poses
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1109/BRACIS.2019.00134 http://hdl.handle.net/11449/198320 |
Resumo: | The advances in video capture, storage and sharing technologies have caused a high demand in techniques for automatic recognition of humans actions. Among the main applications, we can highlight surveillance in public places, detection of falls in the elderly, no-checkout-required stores (Amazon Go), self-driving car, inappropriate content posted on the Internet, etc. The automatic recognition of human actions in videos is a challenging task because in order to obtain a good result one has to work with spatial information (e.g., shapes found in a single frame) and temporal information (e.g., movements found across frames). In this work, we present a simple methodology for describing human actions in videos that use extracted data from 2-Dimensional poses. The experimental results show that the proposed technique can encode spatial and temporal information, obtaining competitive accuracy rates compared to state-of-the-art methods. |
id |
UNSP_badc8541e81b24571e7a9a520234557c |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/198320 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Human action recognition using 2D posesHuman action recognitionSpatio-temporal featuresSurveillance systemsVideo sequencesThe advances in video capture, storage and sharing technologies have caused a high demand in techniques for automatic recognition of humans actions. Among the main applications, we can highlight surveillance in public places, detection of falls in the elderly, no-checkout-required stores (Amazon Go), self-driving car, inappropriate content posted on the Internet, etc. The automatic recognition of human actions in videos is a challenging task because in order to obtain a good result one has to work with spatial information (e.g., shapes found in a single frame) and temporal information (e.g., movements found across frames). In this work, we present a simple methodology for describing human actions in videos that use extracted data from 2-Dimensional poses. The experimental results show that the proposed technique can encode spatial and temporal information, obtaining competitive accuracy rates compared to state-of-the-art methods.Federal University of São Carlos - UFSCarFaculty of Sciences - UNESPFederal Institute of Education Science and Technology of São PauloFaculty of Sciences - UNESPUniversidade Federal de São Carlos (UFSCar)Universidade Estadual Paulista (Unesp)Science and Technology of São PauloVarges Da Silva, MuriloNilceu Marana, Aparecido [UNESP]2020-12-12T01:09:37Z2020-12-12T01:09:37Z2019-10-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject747-752http://dx.doi.org/10.1109/BRACIS.2019.00134Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019, p. 747-752.http://hdl.handle.net/11449/19832010.1109/BRACIS.2019.001342-s2.0-85077048571Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengProceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019info:eu-repo/semantics/openAccess2021-10-23T09:20:10Zoai:repositorio.unesp.br:11449/198320Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T16:48:28.668583Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Human action recognition using 2D poses |
title |
Human action recognition using 2D poses |
spellingShingle |
Human action recognition using 2D poses Varges Da Silva, Murilo Human action recognition Spatio-temporal features Surveillance systems Video sequences |
title_short |
Human action recognition using 2D poses |
title_full |
Human action recognition using 2D poses |
title_fullStr |
Human action recognition using 2D poses |
title_full_unstemmed |
Human action recognition using 2D poses |
title_sort |
Human action recognition using 2D poses |
author |
Varges Da Silva, Murilo |
author_facet |
Varges Da Silva, Murilo Nilceu Marana, Aparecido [UNESP] |
author_role |
author |
author2 |
Nilceu Marana, Aparecido [UNESP] |
author2_role |
author |
dc.contributor.none.fl_str_mv |
Universidade Federal de São Carlos (UFSCar) Universidade Estadual Paulista (Unesp) Science and Technology of São Paulo |
dc.contributor.author.fl_str_mv |
Varges Da Silva, Murilo Nilceu Marana, Aparecido [UNESP] |
dc.subject.por.fl_str_mv |
Human action recognition Spatio-temporal features Surveillance systems Video sequences |
topic |
Human action recognition Spatio-temporal features Surveillance systems Video sequences |
description |
The advances in video capture, storage and sharing technologies have caused a high demand in techniques for automatic recognition of humans actions. Among the main applications, we can highlight surveillance in public places, detection of falls in the elderly, no-checkout-required stores (Amazon Go), self-driving car, inappropriate content posted on the Internet, etc. The automatic recognition of human actions in videos is a challenging task because in order to obtain a good result one has to work with spatial information (e.g., shapes found in a single frame) and temporal information (e.g., movements found across frames). In this work, we present a simple methodology for describing human actions in videos that use extracted data from 2-Dimensional poses. The experimental results show that the proposed technique can encode spatial and temporal information, obtaining competitive accuracy rates compared to state-of-the-art methods. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-10-01 2020-12-12T01:09:37Z 2020-12-12T01:09:37Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/conferenceObject |
format |
conferenceObject |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1109/BRACIS.2019.00134 Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019, p. 747-752. http://hdl.handle.net/11449/198320 10.1109/BRACIS.2019.00134 2-s2.0-85077048571 |
url |
http://dx.doi.org/10.1109/BRACIS.2019.00134 http://hdl.handle.net/11449/198320 |
identifier_str_mv |
Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019, p. 747-752. 10.1109/BRACIS.2019.00134 2-s2.0-85077048571 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
747-752 |
dc.source.none.fl_str_mv |
Scopus 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_ |
1808128704266633216 |