Publication:
A multi-threshold approach and a realistic error measure for vanishing point detection in natural landscapes

Simple item page
dc.affiliation.dptoUC3M. Departamento de Teoría de la Señal y Comunicacioneses
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Procesado Multimediaes
dc.contributor.authorGarcía-Faura, Álvaro
dc.contributor.authorFernández Martínez, Fernando
dc.contributor.authorKleinlein, Ricardo
dc.contributor.authorSan Segundo, Rubén
dc.contributor.authorDíaz de María, Fernando
dc.date.accessioned2020-09-16T16:29:40Z
dc.date.available2021-10-01T23:00:05Z
dc.date.issued2019-10-01
dc.description.abstractVanishing Point (VP) detection is a computer vision task that can be useful in many different fields of application. In this work, we present a VP detection algorithm for natural landscape images based on an multi-threshold edge extraction process that combines several representations of an image, and on novel clustering and cluster refinement procedures. Our algorithm identifies a VP candidate in images with single-point perspective and improves detection results on two datasets that have already been tested for this task. Furthermore, we study how VP detection results have been reported in literature, pointing out the main drawbacks of previous approaches. To overcome these drawbacks, we present a novel error measure that is based on a probabilistic consistency measure between edges and VP hypothesis, and that can be tuned to vary the strictness on the results. Our reasoning on how our measure is more correct is supported by an intuitive analysis, simulations and an experimental validation.en
dc.description.sponsorshipThe work leading to these results has been supported by the Span-ish Ministry of Economy and Competitiveness and the Ministry of Science, Innovation and Universities through the ESITUR (MINECO,RTC-2016-5305- 7), CAVIAR (MICINN, TEC2017-84593-C2-1-R), and AMIC (MICINN, TIN2017-85854-C4-4-R) projects (AEI/FEDER, UE).We also gratefully acknowledge the support of NVIDIA Corporation.en
dc.description.statusPublicadoes
dc.format.extent13
dc.identifier.bibliographicCitationEngineering Applications of Artificial Intelligence, (2019), 85, pp.: 713-726.en
dc.identifier.doihttps://doi.org/10.1016/j.engappai.2019.08.001
dc.identifier.issn0952-1976
dc.identifier.publicationfirstpage713
dc.identifier.publicationlastpage726
dc.identifier.publicationtitleEngineering Applications of Artificial Intelligenceen
dc.identifier.publicationvolume85
dc.identifier.urihttps://hdl.handle.net/10016/30822
dc.identifier.uxxiAR/0000024534
dc.language.isoengen
dc.publisherElsevieres
dc.relation.projectIDGobierno de España. TEC2017-84593-C2-1-R/CAVIARes
dc.relation.projectIDGobierno de España. RTC-2016-5305- 7/ESITURes
dc.relation.projectIDGobierno de España. TIN2017-85854-C4-4-R/AMICes
dc.rights© 2019 Elsevier Ltd. All rights reserved.en
dc.rightsAtribución-NoComercial-SinDerivadas 3.0 España*
dc.rights.accessRightsopen accessen
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/*
dc.subject.ecienciaTelecomunicacioneses
dc.subject.otherLandscapesen
dc.subject.otherMulti-thresholden
dc.subject.otherPerspectiveen
dc.subject.otherVanishing pointen
dc.titleA multi-threshold approach and a realistic error measure for vanishing point detection in natural landscapesen
dc.typeresearch article*
dc.type.hasVersionAM*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
multi-threshold_EAAI_2019_ps.pdf
Size:
1.26 MB
Format:
Adobe Portable Document Format
Download
Collections
DTSC - GPM - Artículos de Revistas