Dense monocular Simultaneous Localization and Mapping by direct surfel optimization

Autores
Trabes, Emanuel; Avila, Luis Omar; Dondo Gazzano, Julio Daniel; Sosa Paez, Carlos Federico
Año de publicación
2021
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
This work presents a novel approach for monocular dense Simultaneous Localization and Mapping. The surface to be estimated is represented as a piecewise planar surface, defined as a group of surfels each having as parameters the position and normal. These parameters are directly estimated from the raw camera pixels measurements using a Gauss-Newton iterative process. The representation of the surface as a group of surfels has many advantages. First, it allows recovering robust and accurate pixel depths, without the need to use a computationally demanding depth regularization schema. This has the further advantage of avoiding the use of a physically unlikely surface smoothness prior. What is more, new surfels can be correctly initialized from the information present in nearby surfels, avoiding also the need to use an expensive initialization routine commonly needed in Gauss-Newton methods. The method was written in the GLSL shading language, allowing the use of GPU devices and achieve real-time processing. The method was tested on benchmark datasets, showing both its depth and normal estimation capacity, and its quality to recover the original scene. Results presented in this work showcase the usefulness of the more physically grounded piecewise planar scene depth prior, instead of the more commonly pixel depth independence and smoothness prior.
Fil: Trabes, Emanuel. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Electrónica; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - San Luis; Argentina
Fil: Avila, Luis Omar. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - San Luis; Argentina. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Informática. Laboratorio Investigación y Desarrollo en Inteligencia Computacional; Argentina
Fil: Dondo Gazzano, Julio Daniel. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Electrónica; Argentina
Fil: Sosa Paez, Carlos Federico. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Electrónica; Argentina
Materia
SLAM
Visual Odometry
Monocular
Depth Estimation
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/157661

id CONICETDig_a03559cdd9701bc8484c6e22ea91f63d
oai_identifier_str oai:ri.conicet.gov.ar:11336/157661
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Dense monocular Simultaneous Localization and Mapping by direct surfel optimizationTrabes, EmanuelAvila, Luis OmarDondo Gazzano, Julio DanielSosa Paez, Carlos FedericoSLAMVisual OdometryMonocularDepth Estimationhttps://purl.org/becyt/ford/2.2https://purl.org/becyt/ford/2This work presents a novel approach for monocular dense Simultaneous Localization and Mapping. The surface to be estimated is represented as a piecewise planar surface, defined as a group of surfels each having as parameters the position and normal. These parameters are directly estimated from the raw camera pixels measurements using a Gauss-Newton iterative process. The representation of the surface as a group of surfels has many advantages. First, it allows recovering robust and accurate pixel depths, without the need to use a computationally demanding depth regularization schema. This has the further advantage of avoiding the use of a physically unlikely surface smoothness prior. What is more, new surfels can be correctly initialized from the information present in nearby surfels, avoiding also the need to use an expensive initialization routine commonly needed in Gauss-Newton methods. The method was written in the GLSL shading language, allowing the use of GPU devices and achieve real-time processing. The method was tested on benchmark datasets, showing both its depth and normal estimation capacity, and its quality to recover the original scene. Results presented in this work showcase the usefulness of the more physically grounded piecewise planar scene depth prior, instead of the more commonly pixel depth independence and smoothness prior.Fil: Trabes, Emanuel. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Electrónica; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - San Luis; ArgentinaFil: Avila, Luis Omar. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - San Luis; Argentina. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Informática. Laboratorio Investigación y Desarrollo en Inteligencia Computacional; ArgentinaFil: Dondo Gazzano, Julio Daniel. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Electrónica; ArgentinaFil: Sosa Paez, Carlos Federico. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Electrónica; ArgentinaUniversidad Nacional Autónoma de México2021-12-31info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/157661Trabes, Emanuel; Avila, Luis Omar; Dondo Gazzano, Julio Daniel; Sosa Paez, Carlos Federico; Dense monocular Simultaneous Localization and Mapping by direct surfel optimization; Universidad Nacional Autónoma de México; Journal of Applied Research and Technology; 19; 6; 31-12-2021; 644-6521665-64231665-6423CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://jart.icat.unam.mx/index.php/jart/article/view/991info:eu-repo/semantics/altIdentifier/doi/10.22201/icat.24486736e.2021.19.6.991info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-nd/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T10:22:00Zoai:ri.conicet.gov.ar:11336/157661instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-29 10:22:01.126CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Dense monocular Simultaneous Localization and Mapping by direct surfel optimization
title Dense monocular Simultaneous Localization and Mapping by direct surfel optimization
spellingShingle Dense monocular Simultaneous Localization and Mapping by direct surfel optimization
Trabes, Emanuel
SLAM
Visual Odometry
Monocular
Depth Estimation
title_short Dense monocular Simultaneous Localization and Mapping by direct surfel optimization
title_full Dense monocular Simultaneous Localization and Mapping by direct surfel optimization
title_fullStr Dense monocular Simultaneous Localization and Mapping by direct surfel optimization
title_full_unstemmed Dense monocular Simultaneous Localization and Mapping by direct surfel optimization
title_sort Dense monocular Simultaneous Localization and Mapping by direct surfel optimization
dc.creator.none.fl_str_mv Trabes, Emanuel
Avila, Luis Omar
Dondo Gazzano, Julio Daniel
Sosa Paez, Carlos Federico
author Trabes, Emanuel
author_facet Trabes, Emanuel
Avila, Luis Omar
Dondo Gazzano, Julio Daniel
Sosa Paez, Carlos Federico
author_role author
author2 Avila, Luis Omar
Dondo Gazzano, Julio Daniel
Sosa Paez, Carlos Federico
author2_role author
author
author
dc.subject.none.fl_str_mv SLAM
Visual Odometry
Monocular
Depth Estimation
topic SLAM
Visual Odometry
Monocular
Depth Estimation
purl_subject.fl_str_mv https://purl.org/becyt/ford/2.2
https://purl.org/becyt/ford/2
dc.description.none.fl_txt_mv This work presents a novel approach for monocular dense Simultaneous Localization and Mapping. The surface to be estimated is represented as a piecewise planar surface, defined as a group of surfels each having as parameters the position and normal. These parameters are directly estimated from the raw camera pixels measurements using a Gauss-Newton iterative process. The representation of the surface as a group of surfels has many advantages. First, it allows recovering robust and accurate pixel depths, without the need to use a computationally demanding depth regularization schema. This has the further advantage of avoiding the use of a physically unlikely surface smoothness prior. What is more, new surfels can be correctly initialized from the information present in nearby surfels, avoiding also the need to use an expensive initialization routine commonly needed in Gauss-Newton methods. The method was written in the GLSL shading language, allowing the use of GPU devices and achieve real-time processing. The method was tested on benchmark datasets, showing both its depth and normal estimation capacity, and its quality to recover the original scene. Results presented in this work showcase the usefulness of the more physically grounded piecewise planar scene depth prior, instead of the more commonly pixel depth independence and smoothness prior.
Fil: Trabes, Emanuel. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Electrónica; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - San Luis; Argentina
Fil: Avila, Luis Omar. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - San Luis; Argentina. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Informática. Laboratorio Investigación y Desarrollo en Inteligencia Computacional; Argentina
Fil: Dondo Gazzano, Julio Daniel. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Electrónica; Argentina
Fil: Sosa Paez, Carlos Federico. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Electrónica; Argentina
description This work presents a novel approach for monocular dense Simultaneous Localization and Mapping. The surface to be estimated is represented as a piecewise planar surface, defined as a group of surfels each having as parameters the position and normal. These parameters are directly estimated from the raw camera pixels measurements using a Gauss-Newton iterative process. The representation of the surface as a group of surfels has many advantages. First, it allows recovering robust and accurate pixel depths, without the need to use a computationally demanding depth regularization schema. This has the further advantage of avoiding the use of a physically unlikely surface smoothness prior. What is more, new surfels can be correctly initialized from the information present in nearby surfels, avoiding also the need to use an expensive initialization routine commonly needed in Gauss-Newton methods. The method was written in the GLSL shading language, allowing the use of GPU devices and achieve real-time processing. The method was tested on benchmark datasets, showing both its depth and normal estimation capacity, and its quality to recover the original scene. Results presented in this work showcase the usefulness of the more physically grounded piecewise planar scene depth prior, instead of the more commonly pixel depth independence and smoothness prior.
publishDate 2021
dc.date.none.fl_str_mv 2021-12-31
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/157661
Trabes, Emanuel; Avila, Luis Omar; Dondo Gazzano, Julio Daniel; Sosa Paez, Carlos Federico; Dense monocular Simultaneous Localization and Mapping by direct surfel optimization; Universidad Nacional Autónoma de México; Journal of Applied Research and Technology; 19; 6; 31-12-2021; 644-652
1665-6423
1665-6423
CONICET Digital
CONICET
url http://hdl.handle.net/11336/157661
identifier_str_mv Trabes, Emanuel; Avila, Luis Omar; Dondo Gazzano, Julio Daniel; Sosa Paez, Carlos Federico; Dense monocular Simultaneous Localization and Mapping by direct surfel optimization; Universidad Nacional Autónoma de México; Journal of Applied Research and Technology; 19; 6; 31-12-2021; 644-652
1665-6423
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://jart.icat.unam.mx/index.php/jart/article/view/991
info:eu-repo/semantics/altIdentifier/doi/10.22201/icat.24486736e.2021.19.6.991
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv Universidad Nacional Autónoma de México
publisher.none.fl_str_mv Universidad Nacional Autónoma de México
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1844614210646966272
score 13.070432