Partially obscured human detection based on component detectors using multiple feature descriptors

This paper presents a human detection system based on component detector using multiple feature descriptors. The contribution presents two issues for dealing with the problem of partially obscured human. First, it presents the extension of feature descriptors using multiple scales based Histograms o...

Descripción completa

Detalles Bibliográficos
Autores: Cáceres Hernández, Danilo, Hyun Jo, Kang, Dung Hoang, Van
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2014
País:Panamá
Institución:Universidad Tecnológica de Panamá
Repositorio:Repositorio Institucional de documento digitales de acceso abierto de la UTP
Idioma:inglés
OAI Identifier:oai:ridda2.utp.ac.pa:123456789/5088
Acceso en línea:http://ridda2.utp.ac.pa/handle/123456789/5088
Access Level:acceso abierto
Palabra clave:Boosting machines
parallelogram based Haar-like feature
multiple scale block based HOG features
support vector machine
id PA_7ea0e8b25d41c7ca401c8f4f61354e62
oai_identifier_str oai:ridda2.utp.ac.pa:123456789/5088
network_acronym_str PA
network_name_str Panamá
repository_id_str
spelling Partially obscured human detection based on component detectors using multiple feature descriptorsCáceres Hernández, DaniloHyun Jo, KangDung Hoang, VanBoosting machinesparallelogram based Haar-like featuremultiple scale block based HOG featuressupport vector machineBoosting machinesparallelogram based Haar-like featuremultiple scale block based HOG featuressupport vector machineThis paper presents a human detection system based on component detector using multiple feature descriptors. The contribution presents two issues for dealing with the problem of partially obscured human. First, it presents the extension of feature descriptors using multiple scales based Histograms of Oriented Gradients (HOG) and parallelogram based Haar-like feature (PHF) for improving the accuracy of the system. By using multiple scales based HOG, an extensive feature space allows obtaining high-discriminated features. Otherwise, the PHF is adaptive limb shapes of human in fast computing feature. Second, learning system using boosting classifications based approach is used for training and detecting the partially obscured human. The advantage of boosting is constructing a strong classification by combining a set of weak classifiers. However, the performance of boosting depends on the kernel of weak classifier. Therefore, the hybrid algorithms based on AdaBoost and SVM using the proposed feature descriptors is one of solutions for robust human detection.This paper presents a human detection system based on component detector using multiple feature descriptors. The contribution presents two issues for dealing with the problem of partially obscured human. First, it presents the extension of feature descriptors using multiple scales based Histograms of Oriented Gradients (HOG) and parallelogram based Haar-like feature (PHF) for improving the accuracy of the system. By using multiple scales based HOG, an extensive feature space allows obtaining high-discriminated features. Otherwise, the PHF is adaptive limb shapes of human in fast computing feature. Second, learning system using boosting classifications based approach is used for training and detecting the partially obscured human. The advantage of boosting is constructing a strong classification by combining a set of weak classifiers. However, the performance of boosting depends on the kernel of weak classifier. Therefore, the hybrid algorithms based on AdaBoost and SVM using the proposed feature descriptors is one of solutions for robust human detection.2018-06-28T21:15:27Z2018-06-28T21:15:27Z2018-06-28T21:15:27Z2018-06-28T21:15:27Z2014-08-032014-08-03info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttp://ridda2.utp.ac.pa/handle/123456789/5088http://ridda2.utp.ac.pa/handle/123456789/5088engenghttps://creativecommons.org/licenses/by-nc-sa/4.0/info:eu-repo/semantics/openAccessreponame:Repositorio Institucional de documento digitales de acceso abierto de la UTPinstname:Universidad Tecnológica de Panamáinstacron:U Tecnológica de Panamáoai:ridda2.utp.ac.pa:123456789/50882021-07-06T15:34:54Z
dc.title.none.fl_str_mv Partially obscured human detection based on component detectors using multiple feature descriptors
title Partially obscured human detection based on component detectors using multiple feature descriptors
spellingShingle Partially obscured human detection based on component detectors using multiple feature descriptors
Cáceres Hernández, Danilo
Boosting machines
parallelogram based Haar-like feature
multiple scale block based HOG features
support vector machine
Boosting machines
parallelogram based Haar-like feature
multiple scale block based HOG features
support vector machine
title_short Partially obscured human detection based on component detectors using multiple feature descriptors
title_full Partially obscured human detection based on component detectors using multiple feature descriptors
title_fullStr Partially obscured human detection based on component detectors using multiple feature descriptors
title_full_unstemmed Partially obscured human detection based on component detectors using multiple feature descriptors
title_sort Partially obscured human detection based on component detectors using multiple feature descriptors
dc.creator.none.fl_str_mv Cáceres Hernández, Danilo
Hyun Jo, Kang
Dung Hoang, Van
author Cáceres Hernández, Danilo
author_facet Cáceres Hernández, Danilo
Hyun Jo, Kang
Dung Hoang, Van
author_role author
author2 Hyun Jo, Kang
Dung Hoang, Van
author2_role author
author
dc.subject.none.fl_str_mv Boosting machines
parallelogram based Haar-like feature
multiple scale block based HOG features
support vector machine
Boosting machines
parallelogram based Haar-like feature
multiple scale block based HOG features
support vector machine
topic Boosting machines
parallelogram based Haar-like feature
multiple scale block based HOG features
support vector machine
Boosting machines
parallelogram based Haar-like feature
multiple scale block based HOG features
support vector machine
description This paper presents a human detection system based on component detector using multiple feature descriptors. The contribution presents two issues for dealing with the problem of partially obscured human. First, it presents the extension of feature descriptors using multiple scales based Histograms of Oriented Gradients (HOG) and parallelogram based Haar-like feature (PHF) for improving the accuracy of the system. By using multiple scales based HOG, an extensive feature space allows obtaining high-discriminated features. Otherwise, the PHF is adaptive limb shapes of human in fast computing feature. Second, learning system using boosting classifications based approach is used for training and detecting the partially obscured human. The advantage of boosting is constructing a strong classification by combining a set of weak classifiers. However, the performance of boosting depends on the kernel of weak classifier. Therefore, the hybrid algorithms based on AdaBoost and SVM using the proposed feature descriptors is one of solutions for robust human detection.
publishDate 2014
dc.date.none.fl_str_mv 2014-08-03
2014-08-03
2018-06-28T21:15:27Z
2018-06-28T21:15:27Z
2018-06-28T21:15:27Z
2018-06-28T21:15:27Z
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://ridda2.utp.ac.pa/handle/123456789/5088
http://ridda2.utp.ac.pa/handle/123456789/5088
url http://ridda2.utp.ac.pa/handle/123456789/5088
dc.language.none.fl_str_mv eng
eng
language eng
dc.rights.none.fl_str_mv https://creativecommons.org/licenses/by-nc-sa/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositorio Institucional de documento digitales de acceso abierto de la UTP
instname:Universidad Tecnológica de Panamá
instacron:U Tecnológica de Panamá
instname_str Universidad Tecnológica de Panamá
instacron_str U Tecnológica de Panamá
institution U Tecnológica de Panamá
reponame_str Repositorio Institucional de documento digitales de acceso abierto de la UTP
collection Repositorio Institucional de documento digitales de acceso abierto de la UTP
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1795886107812954112
score 15,811543

Similares en LA Referencia