Close
Metadata

1. Identity statement
Reference TypeJournal Article
Sitemtc-m21c.sid.inpe.br
Holder Codeisadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S
Identifier8JMKD3MGP3W34R/3S29BG5
Repositorysid.inpe.br/mtc-m21c/2018/10.10.12.23
Last Update2018:10.10.12.23.56 (UTC) simone
Metadata Repositorysid.inpe.br/mtc-m21c/2018/10.10.12.23.56
Metadata Last Update2019:01.14.17.06.36 (UTC) administrator
DOI10.3390/rs10091435
ISSN2072-4292
Citation KeyLotteHaaKarAraShi:2018:CaStUs
Title3D Façade Labeling over Complex Scenarios: A Case Study Using Convolutional Neural Network and Structure-From-Motion
Year2018
MonthSept.
Access Date2024, May 22
Type of Workjournal article
Secondary TypePRE PI
Number of Files1
Size28181 KiB
2. Context
Author1 Lotte, Rodolfo Georjute
2 Haala, Norbert
3 Karpina, Mateusz
4 Aragão, Luiz Eduardo Oliveira e Cruz de
5 Shimabukuro, Yosio Edemir
Resume Identifier1
2
3
4
5 8JMKD3MGP5W/3C9JJCQ
ORCID1 0000-0001-5729-5733
Group1 SER-SRE-SESPG-INPE-MCTIC-GOV-BR
2
3
4 DIDSR-CGOBT-INPE-MCTIC-GOV-BR
5 DIDSR-CGOBT-INPE-MCTIC-GOV-BR
Affiliation1 Instituto Nacional de Pesquisas Espaciais (INPE)
2 University of Stuttgart
3 Wroclaw University of Environmental and Life Sciences
4 Instituto Nacional de Pesquisas Espaciais (INPE)
5 Instituto Nacional de Pesquisas Espaciais (INPE)
Author e-Mail Address1 lotte@dsr.inpe.br
2 norbert.haala@ifp.uni-stuttgart.de
3 mateusz.karpina@igig.up.wroc.pl
4 laragao@dsr.inpe.br
5 yosio@dsr.inpe.br
JournalRemote Sensing
Volume10
Number9
Pagese1435
Secondary MarkB3_GEOGRAFIA B3_ENGENHARIAS_I B4_GEOCIÊNCIAS B4_CIÊNCIAS_AMBIENTAIS B5_CIÊNCIAS_AGRÁRIAS_I
History (UTC)2018-10-10 12:23:56 :: simone -> administrator ::
2018-10-10 12:23:56 :: administrator -> simone :: 2018
2018-10-10 12:24:30 :: simone -> administrator :: 2018
2019-01-14 17:06:36 :: administrator -> simone :: 2018
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Content TypeExternal Contribution
Version Typepublisher
Keywordsfaçade feature detection
3D reconstruction
deep-learning
structure-from-motion
AbstractUrban environments are regions in which spectral variability and spatial variability are extremely high, with a huge range of shapes and sizes, and they also demand high resolution images for applications involving their study. Due to the fact that these environments can grow even more over time, applications related to their monitoring tend to turn to autonomous intelligent systems, which together with remote sensing data could help or even predict daily life situations. The task of mapping cities by autonomous operators was usually carried out by aerial optical images due to its scale and resolution; however new scientific questions have arisen, and this has led research into a new era of highly-detailed data extraction. For many years, using artificial neural models to solve complex problems such as automatic image classification was commonplace, owing much of their popularity to their ability to adapt to complex situations without needing human intervention. In spite of that, their popularity declined in the mid-2000s, mostly due to the complex and time-consuming nature of their methods and workflows. However, newer neural network architectures have brought back the interest in their application for autonomous classifiers, especially for image classification purposes. Convolutional Neural Networks (CNN) have been a trend for pixel-wise image segmentation, showing flexibility when detecting and classifying any kind of object, even in situations where humans failed to perceive differences, such as in city scenarios. In this paper, we aim to explore and experiment with state-of-the-art technologies to semantically label 3D urban models over complex scenarios. To achieve these goals, we split the problem into two main processing lines: first, how to correctly label the façade features in the 2D domain, where a supervised CNN is used to segment ground-based façade images into six feature classes, roof, window, wall, door, balcony and shop; second, a Structure-from-Motion (SfM) and Multi-View-Stereo (MVS) workflow is used to extract the geometry of the façade, wherein the segmented images in the previous stage are then used to label the generated mesh by a reverse ray-tracing technique. This paper demonstrates that the proposed methodology is robust in complex scenarios. The façade feature inferences have reached up to 93% accuracy over most of the datasets used. Although it still presents some deficiencies in unknown architectural styles and needs some improvements to be made regarding 3D-labeling, we present a consistent and simple methodology to handle the problem.
AreaSRE
Arrangement 1urlib.net > BDMCI > Fonds > Produção anterior à 2021 > DIDSR > 3D Façade Labeling...
Arrangement 2urlib.net > BDMCI > Fonds > Produção pgr ATUAIS > SER > 3D Façade Labeling...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 10/10/2018 09:23 1.0 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGP3W34R/3S29BG5
zipped data URLhttp://urlib.net/zip/8JMKD3MGP3W34R/3S29BG5
Languageen
Target Filelotte_3d.pdf
User Groupsimone
Reader Groupadministrator
simone
Visibilityshown
Archiving Policyallowpublisher allowfinaldraft
Update Permissionnot transferred
5. Allied materials
Next Higher Units8JMKD3MGPCW/3ER446E
8JMKD3MGPCW/3F3NU5S
Citing Item Listsid.inpe.br/bibdigital/2013/09.13.21.11 4
sid.inpe.br/bibdigital/2013/10.18.22.34 2
DisseminationWEBSCI; PORTALCAPES; MGA; COMPENDEX; SCOPUS.
Host Collectionurlib.net/www/2017/11.22.19.04
6. Notes
Empty Fieldsalternatejournal archivist callnumber copyholder copyright creatorhistory descriptionlevel e-mailaddress format isbn label lineage mark mirrorrepository nextedition notes parameterlist parentrepositories previousedition previouslowerunit progress project readpermission rightsholder schedulinginformation secondarydate secondarykey session shorttitle sponsor subject tertiarymark tertiarytype url
7. Description control
e-Mail (login)simone
update 


Close