The design of a robust 3D Reconstruction system for video sequences in non controlled environments

Along this thesis, a novel and robust approach for obtaining 3D models from video sequences captured with hand-held cameras is adressed. This work defines a fully automatic pipeline that is able to deal with diferent types of sequences and acquiring devices. The designed and implemented system follo...

Descripción completa

Detalles Bibliográficos
Autor: Herrero Molina, Nicolás
Tipo de recurso: tesis de maestría
Fecha de publicación:2010
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2099.1/21344
Acceso en línea:https://hdl.handle.net/2099.1/21344
Access Level:acceso abierto
Palabra clave:Image processing--Digital techniques
Three-dimensional display systems
Imatges -- Processament -- Tècniques digitals
Visualització tridimensional (Informàtica)
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
id ES_4f75dc69bbb0031663c1a085471b1a0d
oai_identifier_str oai:upcommons.upc.edu:2099.1/21344
network_acronym_str ES
network_name_str España
repository_id_str
spelling The design of a robust 3D Reconstruction system for video sequences in non controlled environmentsHerrero Molina, NicolásImage processing--Digital techniquesThree-dimensional display systemsImatges -- Processament -- Tècniques digitalsVisualització tridimensional (Informàtica)Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeoAlong this thesis, a novel and robust approach for obtaining 3D models from video sequences captured with hand-held cameras is adressed. This work defines a fully automatic pipeline that is able to deal with diferent types of sequences and acquiring devices. The designed and implemented system follows a divide and conquer approach. An smart frame decimation process reduces the temporal redundancy of the input video sequence and selects the best conditioned frames for the reconstruction step. Next, the video is split into overlapped clips with a fixed and small number of Key-frames. This allows to parallelize the Structure and Motion process which translates into a dramatic reduction in the computational complexity. The short length of the clips allows an intensive search for the best solution at each step of the reconstruction, which improves the overall system performance. The process of feature tracking is embedded within the reconstruction loop for each clip as a difference with other approaches. The last contribution of this thesis is a final registration step that merges all the processed clips to the same coordinate frame. This last step consists on a set of linear algorithms that combine information of the structure (3D points) and motion (cameras) shared by partial reconstructions of the same static scene to more accurately estimate their registration to the same coordinate system. The performance for the presented algorithm as well as for the global system is demonstrated in experiments with real data.Universitat Politècnica de CatalunyaLandabaso Diaz, José LuísMarqués Acosta, Fernando20102010-02-1020142014-05-08master thesishttp://purl.org/coar/resource_type/c_bdccNAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/2099.1/21344reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2099.1/213442026-05-27T15:37:01Z
dc.title.none.fl_str_mv The design of a robust 3D Reconstruction system for video sequences in non controlled environments
title The design of a robust 3D Reconstruction system for video sequences in non controlled environments
spellingShingle The design of a robust 3D Reconstruction system for video sequences in non controlled environments
Herrero Molina, Nicolás
Image processing--Digital techniques
Three-dimensional display systems
Imatges -- Processament -- Tècniques digitals
Visualització tridimensional (Informàtica)
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
title_short The design of a robust 3D Reconstruction system for video sequences in non controlled environments
title_full The design of a robust 3D Reconstruction system for video sequences in non controlled environments
title_fullStr The design of a robust 3D Reconstruction system for video sequences in non controlled environments
title_full_unstemmed The design of a robust 3D Reconstruction system for video sequences in non controlled environments
title_sort The design of a robust 3D Reconstruction system for video sequences in non controlled environments
dc.creator.none.fl_str_mv Herrero Molina, Nicolás
author Herrero Molina, Nicolás
author_facet Herrero Molina, Nicolás
author_role author
dc.contributor.none.fl_str_mv Landabaso Diaz, José Luís
Marqués Acosta, Fernando
dc.subject.none.fl_str_mv Image processing--Digital techniques
Three-dimensional display systems
Imatges -- Processament -- Tècniques digitals
Visualització tridimensional (Informàtica)
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
topic Image processing--Digital techniques
Three-dimensional display systems
Imatges -- Processament -- Tècniques digitals
Visualització tridimensional (Informàtica)
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
description Along this thesis, a novel and robust approach for obtaining 3D models from video sequences captured with hand-held cameras is adressed. This work defines a fully automatic pipeline that is able to deal with diferent types of sequences and acquiring devices. The designed and implemented system follows a divide and conquer approach. An smart frame decimation process reduces the temporal redundancy of the input video sequence and selects the best conditioned frames for the reconstruction step. Next, the video is split into overlapped clips with a fixed and small number of Key-frames. This allows to parallelize the Structure and Motion process which translates into a dramatic reduction in the computational complexity. The short length of the clips allows an intensive search for the best solution at each step of the reconstruction, which improves the overall system performance. The process of feature tracking is embedded within the reconstruction loop for each clip as a difference with other approaches. The last contribution of this thesis is a final registration step that merges all the processed clips to the same coordinate frame. This last step consists on a set of linear algorithms that combine information of the structure (3D points) and motion (cameras) shared by partial reconstructions of the same static scene to more accurately estimate their registration to the same coordinate system. The performance for the presented algorithm as well as for the global system is demonstrated in experiments with real data.
publishDate 2010
dc.date.none.fl_str_mv 2010
2010-02-10
2014
2014-05-08
dc.type.none.fl_str_mv master thesis
http://purl.org/coar/resource_type/c_bdcc
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv https://hdl.handle.net/2099.1/21344
url https://hdl.handle.net/2099.1/21344
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 Universitat Politècnica de Catalunya
publisher.none.fl_str_mv Universitat Politècnica de Catalunya
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869407821362102272
score 15.300724

Similares en LA Referencia