3D image reconstruction after traffic accident
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10773/35183 |
Resumo: | In the investigation of a road traffic accident, it is crucial to obtain a sufficiently detailed information model of the scene. In recent years, the study of digital 3D reconstruction has seen great progress and has been applied to many fields, for its effectiveness in correctly capturing realworld data. The process involves mapping a physical space to a set of points in a digital space, forming a point cloud mesh. This mesh is then processed and transformed into other 3D products, such as triangular models and textures. There are multiple approaches to obtain the point cloud data, most notably, based on laser-scanning, like LiDAR. While these techniques yield very accurate results, they are typically very expensive, lengthy and difficult to use. In traffic accident investigation, it is necessary, not only to obtain an accurate model of the scene, but also to do so as quickly as possible, in order to minimise the disruption of regular traffic. Photogrammtery is a 3D reconstruction technique which obtains spatial information from photographic images. A recent application of photogrammetry uses drones to acquire these images. Drones can be used to fly over an area and capture images from a wide variety of vantage points and different angles. Combined with their relatively low cost and great flexibility, this makes them ideal for data collection and monitoring terrain with difficult access. Moreover, a drone can survey a large area very quickly, without the need to set up control stations as is the case with most LiDAR approaches. This work aims to analyse the process of 3D reconstruction from a set images of real traffic accidents acquired by drone. The various stages of generating 3D products, such as point clouds and triangular meshes are studied, in order to obtain a reliable representation of the accident scenes. For this purpose, commercial and other presently used software and algorithms are tested and compared in the generation of these 3D representations as well as which factors and generation parameters have the greatest influence in the quality of the final products. |
id |
RCAP_0dbe30a318bd2f2b7464ed6451c218df |
---|---|
oai_identifier_str |
oai:ria.ua.pt:10773/35183 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
3D image reconstruction after traffic accidentPhotogrammetry3D reconstructionDroneTraffic accidentsPoint cloud3D modelIn the investigation of a road traffic accident, it is crucial to obtain a sufficiently detailed information model of the scene. In recent years, the study of digital 3D reconstruction has seen great progress and has been applied to many fields, for its effectiveness in correctly capturing realworld data. The process involves mapping a physical space to a set of points in a digital space, forming a point cloud mesh. This mesh is then processed and transformed into other 3D products, such as triangular models and textures. There are multiple approaches to obtain the point cloud data, most notably, based on laser-scanning, like LiDAR. While these techniques yield very accurate results, they are typically very expensive, lengthy and difficult to use. In traffic accident investigation, it is necessary, not only to obtain an accurate model of the scene, but also to do so as quickly as possible, in order to minimise the disruption of regular traffic. Photogrammtery is a 3D reconstruction technique which obtains spatial information from photographic images. A recent application of photogrammetry uses drones to acquire these images. Drones can be used to fly over an area and capture images from a wide variety of vantage points and different angles. Combined with their relatively low cost and great flexibility, this makes them ideal for data collection and monitoring terrain with difficult access. Moreover, a drone can survey a large area very quickly, without the need to set up control stations as is the case with most LiDAR approaches. This work aims to analyse the process of 3D reconstruction from a set images of real traffic accidents acquired by drone. The various stages of generating 3D products, such as point clouds and triangular meshes are studied, in order to obtain a reliable representation of the accident scenes. For this purpose, commercial and other presently used software and algorithms are tested and compared in the generation of these 3D representations as well as which factors and generation parameters have the greatest influence in the quality of the final products.Na investigação de acidentes de trânsito rodoviário, a obtenção de um modelo de informação suficientemente detalhado do local é crucial. Nos últimos anos, tem havido um grande progresso no estudo de reconstrução digital 3D e tem sido aplicada a vários campos, pela sua eficácia na correcta captura de dados do mundo real. O processo involve o mapeamento de um espaço físico para um conjunto de pontos num espaço digital, resultando numa nuvem de pontos. Esta nuvem pode ser, então, processada e transformada noutros produtos 3D como modelos triangulares e texturas. Existem várias abordagens à obtenção de uma nuvem de pontos, tais como baseadas em digitalização a laser, como LiDAR. Apesar destas técnicas conseguirem obter resultados muito apurados, têm associado, tipicamente, elevados requisitos de tempo e custo, bem como dificuldade de uso. Numa investigação de um acidente de trânsito, é necessário, não só a obtenção de um modelo correcto do espaço, mas também fazê-lo o mais rápido possível, de modo a causar o mínimo distúrbio no trânsito regular. A fotogrametria é uma técnica de reconstrução 3D, que obtém informação espacial a partir de imagens fotográficas. Uma recente aplicação da fotogrametria faz uso de drones para a captura das imagens. Drones podem ser usados para sobrevoar uma área enquanto capturam imagens de várias posições e ângulos diferentes. Aliado ao seu relativo baixo custo e grande flexibilidade, isto torna-os ideais para o recolhimento de dados e monitorização de terrenos de difícil acesso. Para além disso, um drone pode percorrer uma grande área em tempo reduzido, sem a necessidade de montar postos de controlo, como é o caso de maior parte das técnicas LiDAR. Este trabalho tem por objectivo analisar o processo de reconstrucção 3D a partir de um conjunto de imagens de acidentes reais obtidas por drones. As várias etapas da geração de produtos 3D, como nuvens de pontos e modelos triangulares são estudadas, de modo a obter uma correcta representação dos acidentes. Para o efeito, são testados e comparados programas e algoritmos comerciais e usados actualmente, bem como os principais factores e parâmetros que mais influenciam a qualidade dos resultados finais.2022-11-15T14:00:24Z2022-07-21T00:00:00Z2022-07-21info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10773/35183engValério, Pedro Miguel Soaresinfo: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:RCAAP2024-02-22T12:07:50Zoai:ria.ua.pt:10773/35183Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:06:17.550629Repositório 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 |
3D image reconstruction after traffic accident |
title |
3D image reconstruction after traffic accident |
spellingShingle |
3D image reconstruction after traffic accident Valério, Pedro Miguel Soares Photogrammetry 3D reconstruction Drone Traffic accidents Point cloud 3D model |
title_short |
3D image reconstruction after traffic accident |
title_full |
3D image reconstruction after traffic accident |
title_fullStr |
3D image reconstruction after traffic accident |
title_full_unstemmed |
3D image reconstruction after traffic accident |
title_sort |
3D image reconstruction after traffic accident |
author |
Valério, Pedro Miguel Soares |
author_facet |
Valério, Pedro Miguel Soares |
author_role |
author |
dc.contributor.author.fl_str_mv |
Valério, Pedro Miguel Soares |
dc.subject.por.fl_str_mv |
Photogrammetry 3D reconstruction Drone Traffic accidents Point cloud 3D model |
topic |
Photogrammetry 3D reconstruction Drone Traffic accidents Point cloud 3D model |
description |
In the investigation of a road traffic accident, it is crucial to obtain a sufficiently detailed information model of the scene. In recent years, the study of digital 3D reconstruction has seen great progress and has been applied to many fields, for its effectiveness in correctly capturing realworld data. The process involves mapping a physical space to a set of points in a digital space, forming a point cloud mesh. This mesh is then processed and transformed into other 3D products, such as triangular models and textures. There are multiple approaches to obtain the point cloud data, most notably, based on laser-scanning, like LiDAR. While these techniques yield very accurate results, they are typically very expensive, lengthy and difficult to use. In traffic accident investigation, it is necessary, not only to obtain an accurate model of the scene, but also to do so as quickly as possible, in order to minimise the disruption of regular traffic. Photogrammtery is a 3D reconstruction technique which obtains spatial information from photographic images. A recent application of photogrammetry uses drones to acquire these images. Drones can be used to fly over an area and capture images from a wide variety of vantage points and different angles. Combined with their relatively low cost and great flexibility, this makes them ideal for data collection and monitoring terrain with difficult access. Moreover, a drone can survey a large area very quickly, without the need to set up control stations as is the case with most LiDAR approaches. This work aims to analyse the process of 3D reconstruction from a set images of real traffic accidents acquired by drone. The various stages of generating 3D products, such as point clouds and triangular meshes are studied, in order to obtain a reliable representation of the accident scenes. For this purpose, commercial and other presently used software and algorithms are tested and compared in the generation of these 3D representations as well as which factors and generation parameters have the greatest influence in the quality of the final products. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-11-15T14:00:24Z 2022-07-21T00:00:00Z 2022-07-21 |
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/10773/35183 |
url |
http://hdl.handle.net/10773/35183 |
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_ |
1799137718087712768 |