Pedestrian tracking and re-identification on top-view multi-camera system
Autor(a) principal: | |
---|---|
Data de Publicação: | 2018 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10773/25978 |
Resumo: | Understanding movement patterns inside retail areas is an information that is very useful nowadays, with several systems already developed to count and track pedestrians in those areas. The goal of this dissertation is to develop a system capable of counting, tracking, but mainly re-identifying pedestrians across multiple cameras with top-view, so that we can detect and analyze movement patterns in retail areas or similar applications. The work was divided in four important stages: the study and understanding of various systems that are already developed and the available algorithms; choosing the path to take in order to complete the proposed goals; video capture of adequate footage in order to simulate real scenarios as best as possible; test the developed algorithms and validate the obtained results. Results show that this system is capable of extracting interesting information regarding movement patterns and also capable to re-identify pedestrians across multiple cameras. However, this system might need to be adapted for real life scenarios with a bigger number of pedestrian passages. |
id |
RCAP_bd285a6a9f8c43a939889f7ad47e7258 |
---|---|
oai_identifier_str |
oai:ria.ua.pt:10773/25978 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Pedestrian tracking and re-identification on top-view multi-camera systemComputer visionRe-identificationPedestrian trackingUnderstanding movement patterns inside retail areas is an information that is very useful nowadays, with several systems already developed to count and track pedestrians in those areas. The goal of this dissertation is to develop a system capable of counting, tracking, but mainly re-identifying pedestrians across multiple cameras with top-view, so that we can detect and analyze movement patterns in retail areas or similar applications. The work was divided in four important stages: the study and understanding of various systems that are already developed and the available algorithms; choosing the path to take in order to complete the proposed goals; video capture of adequate footage in order to simulate real scenarios as best as possible; test the developed algorithms and validate the obtained results. Results show that this system is capable of extracting interesting information regarding movement patterns and also capable to re-identify pedestrians across multiple cameras. However, this system might need to be adapted for real life scenarios with a bigger number of pedestrian passages.Ter alguma noção dos padrões de movimento dentro de centros comerciais e áreas de venda a retalho é uma informação cada vez mais procurada nos dias de hoje, com vários sistemas já desenvolvidos para contagem de pessoas e alguns com a possibilidade de acompanhar o percurso dessas pessoas dentro do estabelecimento comercial. Esta dissertação tem como objectivo desenvolver um sistema que permita contar o número de pessoas que passa numa dada àrea, juntamente com o percurso feito por cada pessoa, mas principalmente conseguir re-identificar pessoas entre câmeras, com o objectivo de permitir detetar e analisar padrões de movimento em centros comerciais ou aplicações semelhantes. O trabalho foi dividido em quatro partes importantes: o estudo dos sistemas já no mercado e dos algoritmos disponíveis; definição do caminho a seguir para atingir os objectivos; captura de vídeos adequados de forma a simular situações o mais realistas possíveis; testar os algoritmos e validar os resultados obtidos. Os resultados indicam que este sistema permite extrair informação interessante relativamente a padrões de movimento e re-identificação de pessoas, no entanto o sistema pode ter de ser adaptado para sistemas com um número muito mais elevado de passagens.2019-05-09T08:47:37Z2018-01-01T00:00:00Z2018info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10773/25978TID:202233804engBóia, Rui Gonçalo Barreto Abrantesinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-02-22T11:50:21Zoai:ria.ua.pt:10773/25978Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T02:59:06.448980Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Pedestrian tracking and re-identification on top-view multi-camera system |
title |
Pedestrian tracking and re-identification on top-view multi-camera system |
spellingShingle |
Pedestrian tracking and re-identification on top-view multi-camera system Bóia, Rui Gonçalo Barreto Abrantes Computer vision Re-identification Pedestrian tracking |
title_short |
Pedestrian tracking and re-identification on top-view multi-camera system |
title_full |
Pedestrian tracking and re-identification on top-view multi-camera system |
title_fullStr |
Pedestrian tracking and re-identification on top-view multi-camera system |
title_full_unstemmed |
Pedestrian tracking and re-identification on top-view multi-camera system |
title_sort |
Pedestrian tracking and re-identification on top-view multi-camera system |
author |
Bóia, Rui Gonçalo Barreto Abrantes |
author_facet |
Bóia, Rui Gonçalo Barreto Abrantes |
author_role |
author |
dc.contributor.author.fl_str_mv |
Bóia, Rui Gonçalo Barreto Abrantes |
dc.subject.por.fl_str_mv |
Computer vision Re-identification Pedestrian tracking |
topic |
Computer vision Re-identification Pedestrian tracking |
description |
Understanding movement patterns inside retail areas is an information that is very useful nowadays, with several systems already developed to count and track pedestrians in those areas. The goal of this dissertation is to develop a system capable of counting, tracking, but mainly re-identifying pedestrians across multiple cameras with top-view, so that we can detect and analyze movement patterns in retail areas or similar applications. The work was divided in four important stages: the study and understanding of various systems that are already developed and the available algorithms; choosing the path to take in order to complete the proposed goals; video capture of adequate footage in order to simulate real scenarios as best as possible; test the developed algorithms and validate the obtained results. Results show that this system is capable of extracting interesting information regarding movement patterns and also capable to re-identify pedestrians across multiple cameras. However, this system might need to be adapted for real life scenarios with a bigger number of pedestrian passages. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018-01-01T00:00:00Z 2018 2019-05-09T08:47:37Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10773/25978 TID:202233804 |
url |
http://hdl.handle.net/10773/25978 |
identifier_str_mv |
TID:202233804 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799137644801687552 |