Coarse-to-Fine Adaptive People Detection for Video Sequences by Maximizing Mutual Information

Applying people detectors to unseen data is challenging since patterns distributions, such as viewpoints, motion, poses, backgrounds, occlusions and people sizes, may significantly differ from the ones of the training dataset. In this paper, we propose a coarse-to-fine framework to adapt frame by fr...

Descripción completa

Detalles Bibliográficos
Autores: García Martín, Álvaro, San Miguel Avedillo, Juan Carlos, Martínez Sánchez, José María
Tipo de recurso: artículo
Fecha de publicación:2018
País:España
Institución:Universidad Autónoma de Madrid
Repositorio:Biblos-e Archivo. Repositorio Institucional de la UAM
Idioma:inglés
OAI Identifier:oai:repositorio.uam.es:10486/689969
Acceso en línea:http://hdl.handle.net/10486/689969
https://dx.doi.org/10.3390/s19010004
Access Level:acceso abierto
Palabra clave:People detection
Detector adaptation
Pair-wise correlation
Telecomunicaciones
id ES_565e5349da82c967ee4054923ab4e453
oai_identifier_str oai:repositorio.uam.es:10486/689969
network_acronym_str ES
network_name_str España
repository_id_str
spelling Coarse-to-Fine Adaptive People Detection for Video Sequences by Maximizing Mutual InformationGarcía Martín, ÁlvaroSan Miguel Avedillo, Juan CarlosMartínez Sánchez, José MaríaPeople detectionDetector adaptationPair-wise correlationTelecomunicacionesApplying people detectors to unseen data is challenging since patterns distributions, such as viewpoints, motion, poses, backgrounds, occlusions and people sizes, may significantly differ from the ones of the training dataset. In this paper, we propose a coarse-to-fine framework to adapt frame by frame people detectors during runtime classification, without requiring any additional manually labeled ground truth apart from the offline training of the detection model. Such adaptation make use of multiple detectors mutual information, i.e., similarities and dissimilarities of detectors estimated and agreed by pair-wise correlating their outputs. Globally, the proposed adaptation discriminates between relevant instants in a video sequence, i.e., identifies the representative frames for an adaptation of the system. Locally, the proposed adaptation identifies the best configuration (i.e., detection threshold) of each detector under analysis, maximizing the mutual information to obtain the detection threshold of each detector. The proposed coarse-to-fine approach does not require training the detectors for each new scenario and uses standard people detector outputs, i.e., bounding boxes. The experimental results demonstrate that the proposed approach outperforms state-of-the-art detectors whose optimal threshold configurations are previously determined and fixed from offline training dataThis work has been partially supported by the Spanish government under the project TEC2014-53176-R (HAVideo)MDPIDepartamento de Tecnología Electrónica y de las ComunicacionesEscuela Politécnica SuperiorTratamiento e Interpretación de Vídeo (ING EPS-006)20182018-12-20research articlehttp://purl.org/coar/resource_type/c_2df8fbb1VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10486/689969https://dx.doi.org/10.3390/s19010004reponame:Biblos-e Archivo. Repositorio Institucional de la UAMinstname:Universidad Autónoma de MadridInglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:repositorio.uam.es:10486/6899692026-06-23T12:46:27Z
dc.title.none.fl_str_mv Coarse-to-Fine Adaptive People Detection for Video Sequences by Maximizing Mutual Information
title Coarse-to-Fine Adaptive People Detection for Video Sequences by Maximizing Mutual Information
spellingShingle Coarse-to-Fine Adaptive People Detection for Video Sequences by Maximizing Mutual Information
García Martín, Álvaro
People detection
Detector adaptation
Pair-wise correlation
Telecomunicaciones
title_short Coarse-to-Fine Adaptive People Detection for Video Sequences by Maximizing Mutual Information
title_full Coarse-to-Fine Adaptive People Detection for Video Sequences by Maximizing Mutual Information
title_fullStr Coarse-to-Fine Adaptive People Detection for Video Sequences by Maximizing Mutual Information
title_full_unstemmed Coarse-to-Fine Adaptive People Detection for Video Sequences by Maximizing Mutual Information
title_sort Coarse-to-Fine Adaptive People Detection for Video Sequences by Maximizing Mutual Information
dc.creator.none.fl_str_mv García Martín, Álvaro
San Miguel Avedillo, Juan Carlos
Martínez Sánchez, José María
author García Martín, Álvaro
author_facet García Martín, Álvaro
San Miguel Avedillo, Juan Carlos
Martínez Sánchez, José María
author_role author
author2 San Miguel Avedillo, Juan Carlos
Martínez Sánchez, José María
author2_role author
author
dc.contributor.none.fl_str_mv Departamento de Tecnología Electrónica y de las Comunicaciones
Escuela Politécnica Superior
Tratamiento e Interpretación de Vídeo (ING EPS-006)
dc.subject.none.fl_str_mv People detection
Detector adaptation
Pair-wise correlation
Telecomunicaciones
topic People detection
Detector adaptation
Pair-wise correlation
Telecomunicaciones
description Applying people detectors to unseen data is challenging since patterns distributions, such as viewpoints, motion, poses, backgrounds, occlusions and people sizes, may significantly differ from the ones of the training dataset. In this paper, we propose a coarse-to-fine framework to adapt frame by frame people detectors during runtime classification, without requiring any additional manually labeled ground truth apart from the offline training of the detection model. Such adaptation make use of multiple detectors mutual information, i.e., similarities and dissimilarities of detectors estimated and agreed by pair-wise correlating their outputs. Globally, the proposed adaptation discriminates between relevant instants in a video sequence, i.e., identifies the representative frames for an adaptation of the system. Locally, the proposed adaptation identifies the best configuration (i.e., detection threshold) of each detector under analysis, maximizing the mutual information to obtain the detection threshold of each detector. The proposed coarse-to-fine approach does not require training the detectors for each new scenario and uses standard people detector outputs, i.e., bounding boxes. The experimental results demonstrate that the proposed approach outperforms state-of-the-art detectors whose optimal threshold configurations are previously determined and fixed from offline training data
publishDate 2018
dc.date.none.fl_str_mv 2018
2018-12-20
dc.type.none.fl_str_mv research article
http://purl.org/coar/resource_type/c_2df8fbb1
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10486/689969
https://dx.doi.org/10.3390/s19010004
url http://hdl.handle.net/10486/689969
https://dx.doi.org/10.3390/s19010004
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:Biblos-e Archivo. Repositorio Institucional de la UAM
instname:Universidad Autónoma de Madrid
instname_str Universidad Autónoma de Madrid
reponame_str Biblos-e Archivo. Repositorio Institucional de la UAM
collection Biblos-e Archivo. Repositorio Institucional de la UAM
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869408374819389440
score 15.198674

Similares en LA Referencia