Manifold Learning-based Clustering Approach Applied to Anomaly Detection in Surveillance Videos
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , , , , , , , , |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.5220/0008974604040412 http://hdl.handle.net/11449/209526 |
Resumo: | The huge increase in the amount of multimedia data available and the pressing need for organizing them in different categories, especially in scenarios where there are no labels available, makes data clustering an essential task in different scenarios. In this work, we present a novel clustering method based on an unsupervised manifold learning algorithm, in which a more effective similarity measure is computed by the manifold learning and used for clustering purposes. The proposed approach is applied to anomaly detection in videos and used in combination with different background segmentation methods to improve their effectiveness. An experimental evaluation is conducted on three different image datasets and one video dataset. The obtained results indicate superior accuracy in most clustering tasks when compared to the baselines. Results also demonstrate that the clustering step can improve the results of background subtraction approaches in the majority of cases. |
id |
UNSP_ee2cba948dc1bec20f727394dfd6925d |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/209526 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Manifold Learning-based Clustering Approach Applied to Anomaly Detection in Surveillance VideosClusteringUnsupervised Manifold LearningAnomaly DetectionVideo SurveillanceThe huge increase in the amount of multimedia data available and the pressing need for organizing them in different categories, especially in scenarios where there are no labels available, makes data clustering an essential task in different scenarios. In this work, we present a novel clustering method based on an unsupervised manifold learning algorithm, in which a more effective similarity measure is computed by the manifold learning and used for clustering purposes. The proposed approach is applied to anomaly detection in videos and used in combination with different background segmentation methods to improve their effectiveness. An experimental evaluation is conducted on three different image datasets and one video dataset. The obtained results indicate superior accuracy in most clustering tasks when compared to the baselines. Results also demonstrate that the clustering step can improve the results of background subtraction approaches in the majority of cases.Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)PetrobrasSao Paulo State Univ, UNESP, Dept Stat Appl Math & Comp, Rio Claro, SP, BrazilSao Paulo State Univ, UNESP, Sch Sci, Bauru, SP, BrazilPetr Brasileiro SA Petrobras, Cenpes, Rio De Janeiro, RJ, BrazilSao Paulo State Univ, UNESP, Dept Stat Appl Math & Comp, Rio Claro, SP, BrazilSao Paulo State Univ, UNESP, Sch Sci, Bauru, SP, BrazilFAPESP: 2013/07375-0FAPESP: 2014/12236-1FAPESP: 2017/25908-6FAPESP: 2018/15597-6FAPESP: 2018/21934-5FAPESP: 2019/07825-1FAPESP: 2019/022055CNPq: 308194/20179CNPq: 307066/2017-7CNPq: 427968/2018-6Petrobras: 2017/00285-6ScitepressUniversidade Estadual Paulista (Unesp)Petr Brasileiro SA PetrobrasLopes, Leonardo Tadeu [UNESP]Valem, Lucas Pascotti [UNESP]Guimaraes Pedronette, Daniel Carlos [UNESP]Guilherme, Ivan Rizzo [UNESP]Papa, Joao Paulo [UNESP]Silva Santana, Marcos Cleison [UNESP]Colombo, DaniloFarinella, G. M.Radeva, P.Braz, J.2021-06-25T12:21:14Z2021-06-25T12:21:14Z2020-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject404-412http://dx.doi.org/10.5220/0008974604040412Proceedings Of The 15th International Joint Conference On Computer Vision, Imaging And Computer Graphics Theory And Applications, Vol 5: Visapp. Setubal: Scitepress, p. 404-412, 2020.http://hdl.handle.net/11449/20952610.5220/0008974604040412WOS:000576655800043Web of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengProceedings Of The 15th International Joint Conference On Computer Vision, Imaging And Computer Graphics Theory And Applications, Vol 5: Visappinfo:eu-repo/semantics/openAccess2021-10-23T19:28:14Zoai:repositorio.unesp.br:11449/209526Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462021-10-23T19:28:14Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Manifold Learning-based Clustering Approach Applied to Anomaly Detection in Surveillance Videos |
title |
Manifold Learning-based Clustering Approach Applied to Anomaly Detection in Surveillance Videos |
spellingShingle |
Manifold Learning-based Clustering Approach Applied to Anomaly Detection in Surveillance Videos Lopes, Leonardo Tadeu [UNESP] Clustering Unsupervised Manifold Learning Anomaly Detection Video Surveillance |
title_short |
Manifold Learning-based Clustering Approach Applied to Anomaly Detection in Surveillance Videos |
title_full |
Manifold Learning-based Clustering Approach Applied to Anomaly Detection in Surveillance Videos |
title_fullStr |
Manifold Learning-based Clustering Approach Applied to Anomaly Detection in Surveillance Videos |
title_full_unstemmed |
Manifold Learning-based Clustering Approach Applied to Anomaly Detection in Surveillance Videos |
title_sort |
Manifold Learning-based Clustering Approach Applied to Anomaly Detection in Surveillance Videos |
author |
Lopes, Leonardo Tadeu [UNESP] |
author_facet |
Lopes, Leonardo Tadeu [UNESP] Valem, Lucas Pascotti [UNESP] Guimaraes Pedronette, Daniel Carlos [UNESP] Guilherme, Ivan Rizzo [UNESP] Papa, Joao Paulo [UNESP] Silva Santana, Marcos Cleison [UNESP] Colombo, Danilo Farinella, G. M. Radeva, P. Braz, J. |
author_role |
author |
author2 |
Valem, Lucas Pascotti [UNESP] Guimaraes Pedronette, Daniel Carlos [UNESP] Guilherme, Ivan Rizzo [UNESP] Papa, Joao Paulo [UNESP] Silva Santana, Marcos Cleison [UNESP] Colombo, Danilo Farinella, G. M. Radeva, P. Braz, J. |
author2_role |
author author author author author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) Petr Brasileiro SA Petrobras |
dc.contributor.author.fl_str_mv |
Lopes, Leonardo Tadeu [UNESP] Valem, Lucas Pascotti [UNESP] Guimaraes Pedronette, Daniel Carlos [UNESP] Guilherme, Ivan Rizzo [UNESP] Papa, Joao Paulo [UNESP] Silva Santana, Marcos Cleison [UNESP] Colombo, Danilo Farinella, G. M. Radeva, P. Braz, J. |
dc.subject.por.fl_str_mv |
Clustering Unsupervised Manifold Learning Anomaly Detection Video Surveillance |
topic |
Clustering Unsupervised Manifold Learning Anomaly Detection Video Surveillance |
description |
The huge increase in the amount of multimedia data available and the pressing need for organizing them in different categories, especially in scenarios where there are no labels available, makes data clustering an essential task in different scenarios. In this work, we present a novel clustering method based on an unsupervised manifold learning algorithm, in which a more effective similarity measure is computed by the manifold learning and used for clustering purposes. The proposed approach is applied to anomaly detection in videos and used in combination with different background segmentation methods to improve their effectiveness. An experimental evaluation is conducted on three different image datasets and one video dataset. The obtained results indicate superior accuracy in most clustering tasks when compared to the baselines. Results also demonstrate that the clustering step can improve the results of background subtraction approaches in the majority of cases. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-01-01 2021-06-25T12:21:14Z 2021-06-25T12:21:14Z |
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/10.5220/0008974604040412 Proceedings Of The 15th International Joint Conference On Computer Vision, Imaging And Computer Graphics Theory And Applications, Vol 5: Visapp. Setubal: Scitepress, p. 404-412, 2020. http://hdl.handle.net/11449/209526 10.5220/0008974604040412 WOS:000576655800043 |
url |
http://dx.doi.org/10.5220/0008974604040412 http://hdl.handle.net/11449/209526 |
identifier_str_mv |
Proceedings Of The 15th International Joint Conference On Computer Vision, Imaging And Computer Graphics Theory And Applications, Vol 5: Visapp. Setubal: Scitepress, p. 404-412, 2020. 10.5220/0008974604040412 WOS:000576655800043 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Proceedings Of The 15th International Joint Conference On Computer Vision, Imaging And Computer Graphics Theory And Applications, Vol 5: Visapp |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
404-412 |
dc.publisher.none.fl_str_mv |
Scitepress |
publisher.none.fl_str_mv |
Scitepress |
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_ |
1803046858382114816 |