Computer vision for traffic and object detection
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10773/41041 |
Resumo: | On average, in the European Union, there were 44 road deaths per million inhabitants in 2021, representing an increase of 5% compared to 2020, but a decrease of 13% compared to 2019, before the pandemic. In Portugal this trend represents the occurrence of 52 road deaths per million inhabitants in 2021. This work aims to improve safety at crosswalks and predict collisions in cities. This work aims to have a significant impact in terms of road safety and protection of users, by improving safety at crosswalks, preventing collisions, reducing accidents and injuries, increasing safety in a public environment, with the versatility to be implemented in other cities. This thesis also aims to demonstrate the benefits of computer vision for the development, control, optimization and safety of a city. It proposed mechanisms to retrieve information from video cameras to analyse mobility and danger situations. This way, we study danger relations in crosswalks, in order to understand how the danger varies in this type of zone, considering cars and pedestrians. The goal will also be to do this study for different zones and verify data sets that can lead us to draw conclusions about a given occurrence and thus activate the necessary means to solve them. The goal of the thesis was the development of algorithms for accident detection and prediction, which allow the city to become more interconnected and more intelligent from a technological point of view. |
id |
RCAP_cc970dfa33bed01c10fc5a6c461176bf |
---|---|
oai_identifier_str |
oai:ria.ua.pt:10773/41041 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Computer vision for traffic and object detectionAccident detectionVehicular collisionCentroid based object trackingCollision avoidanceEdge computingSmart cityVulnerable road usersOn average, in the European Union, there were 44 road deaths per million inhabitants in 2021, representing an increase of 5% compared to 2020, but a decrease of 13% compared to 2019, before the pandemic. In Portugal this trend represents the occurrence of 52 road deaths per million inhabitants in 2021. This work aims to improve safety at crosswalks and predict collisions in cities. This work aims to have a significant impact in terms of road safety and protection of users, by improving safety at crosswalks, preventing collisions, reducing accidents and injuries, increasing safety in a public environment, with the versatility to be implemented in other cities. This thesis also aims to demonstrate the benefits of computer vision for the development, control, optimization and safety of a city. It proposed mechanisms to retrieve information from video cameras to analyse mobility and danger situations. This way, we study danger relations in crosswalks, in order to understand how the danger varies in this type of zone, considering cars and pedestrians. The goal will also be to do this study for different zones and verify data sets that can lead us to draw conclusions about a given occurrence and thus activate the necessary means to solve them. The goal of the thesis was the development of algorithms for accident detection and prediction, which allow the city to become more interconnected and more intelligent from a technological point of view.Em média, na União Europeia, ocorreram 44 mortes na estrada por milhão de habitante em 2021, representando um aumento de 5% face a 2020, mas uma diminuição de 13% face a 2019, antes da pandemia. Em Portugal esta tendência representa a ocorrência de 52 mortes rodoviárias por milhão de habitante em 2021. Este trabalho tem como objetivo melhorar a segurança em passadeiras e prever possíveis colisões nas cidades. O trabalho proposto pretende ter um impacto significativo em termos de segurança rodoviária e proteção de utilizadores, por melhorar a segurança nas passadeiras, prevenir colisões, reduzir acidentes e lesões, aumentando a segurança num ambiente publico, com a versatilidade de poder ser implementado em outras cidades. Esta tese visa também como objetivo demonstrar os benefícios de visão por computador para o desenvolvimento, controlo, otimização e segurança uma cidade. São propostos mecanismos que permitem retirar informação de câmaras de vídeo que permitem analisar a mobilidade e situações de perigo. Desta forma, são estudadas relações de perigo em passadeiras, de maneira a perceber como varia o perigo neste tipo de zonas, considerando carros e peões. O objetivo será também fazer este estudo para zonas diferentes e verificar conjuntos de dados que nos possam levar a tirar conclusões sobre uma dada ocorrência, e assim ativar os meios necessários para os resolver. O objetivo da tese foi o desenvolvimento de algoritmos de deteção e previsão de acidentes, que permitam tornar a cidade mais interligada e mais inteligente do ponto de vista tecnológico.2024-08-03T00:00:00Z2023-07-07T00:00:00Z2023-07-07info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10773/41041engMendes, Marcos André Lopesinfo:eu-repo/semantics/embargoedAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-03-18T01:48:14Zoai:ria.ua.pt:10773/41041Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T04:02:08.981128Repositório 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 |
Computer vision for traffic and object detection |
title |
Computer vision for traffic and object detection |
spellingShingle |
Computer vision for traffic and object detection Mendes, Marcos André Lopes Accident detection Vehicular collision Centroid based object tracking Collision avoidance Edge computing Smart city Vulnerable road users |
title_short |
Computer vision for traffic and object detection |
title_full |
Computer vision for traffic and object detection |
title_fullStr |
Computer vision for traffic and object detection |
title_full_unstemmed |
Computer vision for traffic and object detection |
title_sort |
Computer vision for traffic and object detection |
author |
Mendes, Marcos André Lopes |
author_facet |
Mendes, Marcos André Lopes |
author_role |
author |
dc.contributor.author.fl_str_mv |
Mendes, Marcos André Lopes |
dc.subject.por.fl_str_mv |
Accident detection Vehicular collision Centroid based object tracking Collision avoidance Edge computing Smart city Vulnerable road users |
topic |
Accident detection Vehicular collision Centroid based object tracking Collision avoidance Edge computing Smart city Vulnerable road users |
description |
On average, in the European Union, there were 44 road deaths per million inhabitants in 2021, representing an increase of 5% compared to 2020, but a decrease of 13% compared to 2019, before the pandemic. In Portugal this trend represents the occurrence of 52 road deaths per million inhabitants in 2021. This work aims to improve safety at crosswalks and predict collisions in cities. This work aims to have a significant impact in terms of road safety and protection of users, by improving safety at crosswalks, preventing collisions, reducing accidents and injuries, increasing safety in a public environment, with the versatility to be implemented in other cities. This thesis also aims to demonstrate the benefits of computer vision for the development, control, optimization and safety of a city. It proposed mechanisms to retrieve information from video cameras to analyse mobility and danger situations. This way, we study danger relations in crosswalks, in order to understand how the danger varies in this type of zone, considering cars and pedestrians. The goal will also be to do this study for different zones and verify data sets that can lead us to draw conclusions about a given occurrence and thus activate the necessary means to solve them. The goal of the thesis was the development of algorithms for accident detection and prediction, which allow the city to become more interconnected and more intelligent from a technological point of view. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-07-07T00:00:00Z 2023-07-07 2024-08-03T00:00:00Z |
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/10773/41041 |
url |
http://hdl.handle.net/10773/41041 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/embargoedAccess |
eu_rights_str_mv |
embargoedAccess |
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_ |
1799138193897947136 |