MSP2P: Multi-Scale Point-based Approach for Optimal Crowd Localization Through Perspective Analysis

[EN] Image-based individual localization in densely populated scenes offers practical advantages beyond mere head counting, enabling a broader range of high-level tasks in crowd analysis. Crowd image data contain drastic changes in head sizes caused by the perspective effect. This specific challenge...

Descripción completa

Detalles Bibliográficos
Autores: Redó Nieto, David, Aramburu Retegui, Mikel, García Castaño, Jorge, Sánchez Salmerón, Antonio José|||0000-0003-1896-5356
Tipo de recurso: artículo
Fecha de publicación:2025
País:España
Institución:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:dnet:riunet______::964893f28cfa4f69d136078770c2ecac
Acceso en línea:https://riunet.upv.es/handle/10251/234728
Access Level:acceso abierto
Palabra clave:Crowd localization
Multi-scale
Crowd counting
id ES_242df4537eaffe697a6cbb22fe694425
oai_identifier_str oai:dnet:riunet______::964893f28cfa4f69d136078770c2ecac
network_acronym_str ES
network_name_str España
repository_id_str
spelling MSP2P: Multi-Scale Point-based Approach for Optimal Crowd Localization Through Perspective AnalysisRedó Nieto, DavidAramburu Retegui, MikelGarcía Castaño, JorgeSánchez Salmerón, Antonio José|||0000-0003-1896-5356Crowd localizationMulti-scaleCrowd counting[EN] Image-based individual localization in densely populated scenes offers practical advantages beyond mere head counting, enabling a broader range of high-level tasks in crowd analysis. Crowd image data contain drastic changes in head sizes caused by the perspective effect. This specific challenge has not been addressed in the literature, as existing localization methods do not consider multi-scale features. To alleviate this issue, we propose a novel Multi-Scale Point-to-Point Network (MSP2P) in which a set of experts are in charge of predicting head locations a at different perspective levels. However, the training procedure requires ground-truth scale information for precise one-to-one matching. For this reason, we develop a simple yet effective method that uses neighbor density information to estimate the scale associated with each head location. Extensive experiments demonstrate that our method outperforms most state-of-the-art methods on relevant counting benchmarks without compromising performance.The work described in this paper is performed in the H2020 project STARLIGHT ( sustainable Autonomy and Resilience for LEAs using AI against High Priority Threats ). This project has received funding from the European Union s Horizon 2020 research and innovation program under grant agreement No 101021797.International Association of Computer Science and Information TechnologyDepartamento de Ingeniería de Sistemas y AutomáticaInstituto Universitario de Automática e Informática IndustrialEscuela Técnica Superior de Ingeniería IndustrialEuropean CommissionRepositorio Institucional de la Universitat Politècnica de València Riunet20252025-02-01journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://riunet.upv.es/handle/10251/234728reponame:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valénciainstname:Universitat Politècnica de València (UPV)InglésengEuropean Commission https://doi.org/10.13039/501100000780 H2020 101021797 Sustainable Autonomy and Resilience for LEAs using AI against High priority Threatsopen accesshttp://purl.org/coar/access_right/c_abf2Reconocimiento (by)http://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:dnet:riunet______::964893f28cfa4f69d136078770c2ecac2026-06-13T07:49:27Z
dc.title.none.fl_str_mv MSP2P: Multi-Scale Point-based Approach for Optimal Crowd Localization Through Perspective Analysis
title MSP2P: Multi-Scale Point-based Approach for Optimal Crowd Localization Through Perspective Analysis
spellingShingle MSP2P: Multi-Scale Point-based Approach for Optimal Crowd Localization Through Perspective Analysis
Redó Nieto, David
Crowd localization
Multi-scale
Crowd counting
title_short MSP2P: Multi-Scale Point-based Approach for Optimal Crowd Localization Through Perspective Analysis
title_full MSP2P: Multi-Scale Point-based Approach for Optimal Crowd Localization Through Perspective Analysis
title_fullStr MSP2P: Multi-Scale Point-based Approach for Optimal Crowd Localization Through Perspective Analysis
title_full_unstemmed MSP2P: Multi-Scale Point-based Approach for Optimal Crowd Localization Through Perspective Analysis
title_sort MSP2P: Multi-Scale Point-based Approach for Optimal Crowd Localization Through Perspective Analysis
dc.creator.none.fl_str_mv Redó Nieto, David
Aramburu Retegui, Mikel
García Castaño, Jorge
Sánchez Salmerón, Antonio José|||0000-0003-1896-5356
author Redó Nieto, David
author_facet Redó Nieto, David
Aramburu Retegui, Mikel
García Castaño, Jorge
Sánchez Salmerón, Antonio José|||0000-0003-1896-5356
author_role author
author2 Aramburu Retegui, Mikel
García Castaño, Jorge
Sánchez Salmerón, Antonio José|||0000-0003-1896-5356
author2_role author
author
author
dc.contributor.none.fl_str_mv Departamento de Ingeniería de Sistemas y Automática
Instituto Universitario de Automática e Informática Industrial
Escuela Técnica Superior de Ingeniería Industrial
European Commission
Repositorio Institucional de la Universitat Politècnica de València Riunet
dc.subject.none.fl_str_mv Crowd localization
Multi-scale
Crowd counting
topic Crowd localization
Multi-scale
Crowd counting
description [EN] Image-based individual localization in densely populated scenes offers practical advantages beyond mere head counting, enabling a broader range of high-level tasks in crowd analysis. Crowd image data contain drastic changes in head sizes caused by the perspective effect. This specific challenge has not been addressed in the literature, as existing localization methods do not consider multi-scale features. To alleviate this issue, we propose a novel Multi-Scale Point-to-Point Network (MSP2P) in which a set of experts are in charge of predicting head locations a at different perspective levels. However, the training procedure requires ground-truth scale information for precise one-to-one matching. For this reason, we develop a simple yet effective method that uses neighbor density information to estimate the scale associated with each head location. Extensive experiments demonstrate that our method outperforms most state-of-the-art methods on relevant counting benchmarks without compromising performance.
publishDate 2025
dc.date.none.fl_str_mv 2025
2025-02-01
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
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 https://riunet.upv.es/handle/10251/234728
url https://riunet.upv.es/handle/10251/234728
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv European Commission https://doi.org/10.13039/501100000780 H2020 101021797 Sustainable Autonomy and Resilience for LEAs using AI against High priority Threats
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Reconocimiento (by)
http://creativecommons.org/licenses/by/4.0/
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
Reconocimiento (by)
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv International Association of Computer Science and Information Technology
publisher.none.fl_str_mv International Association of Computer Science and Information Technology
dc.source.none.fl_str_mv reponame:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname:Universitat Politècnica de València (UPV)
instname_str Universitat Politècnica de València (UPV)
reponame_str RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
collection RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869404684038438912
score 15,812429

Similares en LA Referencia