Automatic low baseline stereo in urban areas

In this work we propose a new automatic methodology for computing accurate digital elevation models (DEMs) in urban environments from low baseline stereo pairs that shall be available in the future from a new kind of earth observation satellite. This setting makes both views of the scene similarly,...

Descripción completa

Detalles Bibliográficos
Autores: Igual, Laura, Preciozzi, Javier, Garrido, Luís, Almansa, Andrés, Caselles, Vicente, Rougé, Bernard
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2007
País:España
Institución:Universitat Pompeu Fabra
Repositorio:Repositorio Digital de la UPF
OAI Identifier:oai:repositori.upf.edu:10230/20686
Acceso en línea:http://hdl.handle.net/10230/20686
http://dx.doi.org/10.3934/ipi.2007.1.319
Access Level:acceso abierto
Palabra clave:Anàlisi global (Matemàtica)
Espais simètrics
Stereo vision
Subpixel urban DEMs
Piecewise affine
id ES_fbabf2fd662af329a5ea3adfc5c694ce
oai_identifier_str oai:repositori.upf.edu:10230/20686
network_acronym_str ES
network_name_str España
repository_id_str
spelling Automatic low baseline stereo in urban areasIgual, LauraPreciozzi, JavierGarrido, LuísAlmansa, AndrésCaselles, VicenteRougé, BernardAnàlisi global (Matemàtica)Espais simètricsStereo visionSubpixel urban DEMsPiecewise affineIn this work we propose a new automatic methodology for computing accurate digital elevation models (DEMs) in urban environments from low baseline stereo pairs that shall be available in the future from a new kind of earth observation satellite. This setting makes both views of the scene similarly, thus avoiding occlusions and illumination changes, which are the main disadvantages of the commonly accepted large-baseline configuration. There still remain two crucial technological challenges: (i) precisely estimating DEMs with strong discontinuities and (ii) providing a statistically proven result, automatically. The first one is solved here by a piecewise affine representation that is well adapted to man-made landscapes, whereas the application of computational Gestalt theory introduces reliability and automation. In fact this theory allows us to reduce the number of parameters to be adjusted, and to/ncontrol the number of false detections. This leads to the selection of a suitable segmentation into affine regions (whenever possible) by a novel and completely automatic perceptual grouping method. It also allows us to discriminate e.g. vegetation-dominated regions, where such an affine model does not apply and/na more classical correlation technique should be preferred. In addition we propose here an extension of the classical ”quantized” Gestalt theory to continuous measurements, thus combining its reliability with the precision of variational robust estimation and fine interpolation methods that are necessary in the low baseline case. Such an extension is very general and will be useful for many other applications as well.A. Almansa, J. Preciozzi and L. Igual acknowledge partial support from PDT project number S/C/OP/17/01 (Uruguay). A. Almansa acknowledges additional support from CSIC (Uruguay),CNES, CNRS and ENS Cachan (France), and UPF(Spain). V. Caselles acknowledges partial support by the Departament d’Universitats, Recerca i Societat de la Informació de la Generalitat de Catalunya and by PNPGC project, reference BFM2003-02125.AIMS American Institute of Mathematical SciencesUniversitat Pompeu Fabra201320132007info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/10230/20686http://dx.doi.org/10.3934/ipi.2007.1.319reponame:Repositorio Digital de la UPFinstname:Universitat Pompeu FabraInglésInverse Problems and Imaging. 2007; 1 (2)© AIMS (http://dx.doi.org/10.3934/ipi.2007.1.319)info:eu-repo/semantics/openAccessoai:repositori.upf.edu:10230/206862026-06-12T07:21:37Z
dc.title.none.fl_str_mv Automatic low baseline stereo in urban areas
title Automatic low baseline stereo in urban areas
spellingShingle Automatic low baseline stereo in urban areas
Igual, Laura
Anàlisi global (Matemàtica)
Espais simètrics
Stereo vision
Subpixel urban DEMs
Piecewise affine
title_short Automatic low baseline stereo in urban areas
title_full Automatic low baseline stereo in urban areas
title_fullStr Automatic low baseline stereo in urban areas
title_full_unstemmed Automatic low baseline stereo in urban areas
title_sort Automatic low baseline stereo in urban areas
dc.creator.none.fl_str_mv Igual, Laura
Preciozzi, Javier
Garrido, Luís
Almansa, Andrés
Caselles, Vicente
Rougé, Bernard
author Igual, Laura
author_facet Igual, Laura
Preciozzi, Javier
Garrido, Luís
Almansa, Andrés
Caselles, Vicente
Rougé, Bernard
author_role author
author2 Preciozzi, Javier
Garrido, Luís
Almansa, Andrés
Caselles, Vicente
Rougé, Bernard
author2_role author
author
author
author
author
dc.contributor.none.fl_str_mv Universitat Pompeu Fabra
dc.subject.none.fl_str_mv Anàlisi global (Matemàtica)
Espais simètrics
Stereo vision
Subpixel urban DEMs
Piecewise affine
topic Anàlisi global (Matemàtica)
Espais simètrics
Stereo vision
Subpixel urban DEMs
Piecewise affine
description In this work we propose a new automatic methodology for computing accurate digital elevation models (DEMs) in urban environments from low baseline stereo pairs that shall be available in the future from a new kind of earth observation satellite. This setting makes both views of the scene similarly, thus avoiding occlusions and illumination changes, which are the main disadvantages of the commonly accepted large-baseline configuration. There still remain two crucial technological challenges: (i) precisely estimating DEMs with strong discontinuities and (ii) providing a statistically proven result, automatically. The first one is solved here by a piecewise affine representation that is well adapted to man-made landscapes, whereas the application of computational Gestalt theory introduces reliability and automation. In fact this theory allows us to reduce the number of parameters to be adjusted, and to/ncontrol the number of false detections. This leads to the selection of a suitable segmentation into affine regions (whenever possible) by a novel and completely automatic perceptual grouping method. It also allows us to discriminate e.g. vegetation-dominated regions, where such an affine model does not apply and/na more classical correlation technique should be preferred. In addition we propose here an extension of the classical ”quantized” Gestalt theory to continuous measurements, thus combining its reliability with the precision of variational robust estimation and fine interpolation methods that are necessary in the low baseline case. Such an extension is very general and will be useful for many other applications as well.
publishDate 2007
dc.date.none.fl_str_mv 2007
2013
2013
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10230/20686
http://dx.doi.org/10.3934/ipi.2007.1.319
url http://hdl.handle.net/10230/20686
http://dx.doi.org/10.3934/ipi.2007.1.319
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Inverse Problems and Imaging. 2007; 1 (2)
dc.rights.none.fl_str_mv © AIMS (http://dx.doi.org/10.3934/ipi.2007.1.319)
info:eu-repo/semantics/openAccess
rights_invalid_str_mv © AIMS (http://dx.doi.org/10.3934/ipi.2007.1.319)
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv AIMS American Institute of Mathematical Sciences
publisher.none.fl_str_mv AIMS American Institute of Mathematical Sciences
dc.source.none.fl_str_mv reponame:Repositorio Digital de la UPF
instname:Universitat Pompeu Fabra
instname_str Universitat Pompeu Fabra
reponame_str Repositorio Digital de la UPF
collection Repositorio Digital de la UPF
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869425350907265024
score 15.812429

Similares en LA Referencia