DC FieldValueLanguage
dc.contributor.authorKnura, Martin Michael-
dc.date.accessioned2024-02-21T15:33:24Z-
dc.date.available2024-02-21T15:33:24Z-
dc.date.issued2024-
dc.identifier.issn1523-0406en_US
dc.identifier.urihttps://repos.hcu-hamburg.de/handle/hcu/934-
dc.description.abstractMap generalization is a complex task that requires a high level of spatial cognition, and deep learning techniques have shown in numerous research fields that they could match or even outplay human cognition when knowledge is implicitly in the data. First experiments that apply deep learning techniques to map generalization tasks thereby adapt models from image processing, creating input data by rasterizing spatial vector data. Because image-based learning has major shortcomings for map generalization, this article investigates possibilities to learn directly from vector data, utilizing vector-based encoding schemes. First, we enhance preprocessing methods to match essential properties of deep learning models – namely regularity and feature description – and evaluate the performance of Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Graph Convolutional Neural Networks (GCNN) in combination with a feature-based encoding scheme. The results show that feature descriptors improve the accuracy of all three neural networks, and that the overall performances of the models are quite similar for both polygon and polyline shape classification tasks. In a second step, we implement an exemplary building generalization workflow based on shape classification and template matching, and discuss the generalization results based on a case study.en
dc.language.isoenen_US
dc.publisherTaylor & Francisen_US
dc.relation.ispartofCartography and Geographic Information Scienceen_US
dc.subjectDeep learningen
dc.subjectmap generalizationen
dc.subjectvector dataen
dc.subjectfeature descriptoren
dc.subjectshape classificationen
dc.subjectbuilding generalizationen
dc.subject.ddc004: Informatiken_US
dc.titleLearning from vector data: enhancing vector-based shape encoding and shape classification for map generalization purposesen
dc.typeArticleen_US
dc.type.diniarticle-
dc.type.driverarticle-
dc.rights.cchttps://creativecommons.org/licenses/by-nc-nd/4.0/en_US
dc.type.casraiJournal Article-
dcterms.DCMITypeText-
tuhh.identifier.urnurn:nbn:de:gbv:1373-repos-12038-
tuhh.oai.showtrueen_US
tuhh.publisher.doi10.1080/15230406.2023.2273397-
tuhh.publication.instituteGeodäsie und Geoinformatiken_US
tuhh.type.opus(wissenschaftlicher) Artikel-
tuhh.container.issue1en_US
tuhh.container.volume51en_US
tuhh.container.startpage146en_US
tuhh.container.endpage167en_US
tuhh.type.rdmfalse-
openaire.rightsinfo:eu-repo/semantics/openAccessen_US
item.openairecristypehttp://purl.org/coar/resource_type/c_6501-
item.fulltextWith Fulltext-
item.languageiso639-1en-
item.cerifentitytypePublications-
item.creatorOrcidKnura, Martin Michael-
item.grantfulltextopen-
item.openairetypeArticle-
item.creatorGNDKnura, Martin Michael-
crisitem.author.deptGeodäsie und Geoinformatik-
Appears in CollectionPublikationen (mit Volltext)
Show simple item record

Page view(s)

272
checked on Apr 15, 2024

Download(s)

52
checked on Apr 15, 2024

Google ScholarTM

Check

Export

This item is licensed under a Creative Commons License Creative Commons