Show simple item record

dc.contributor.author
Schnürer, Raimund
dc.contributor.author
Sieber, René
dc.contributor.author
Schmid-Lanter, Jost
dc.contributor.author
Öztireli, A. Cengiz
dc.contributor.author
Hurni, Lorenz
dc.date.accessioned
2021-08-11T15:04:28Z
dc.date.available
2020-10-02T02:46:08Z
dc.date.available
2020-10-02T11:07:09Z
dc.date.available
2021-08-11T15:04:28Z
dc.date.issued
2021
dc.identifier.issn
0008-7041
dc.identifier.issn
1743-2774
dc.identifier.other
10.1080/00087041.2020.1738112
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/444044
dc.description.abstract
In this work, realistically drawn objects are identified on digital maps by convolutional neural networks. For the first two experiments, 6200 images were retrieved from Pinterest. While alternating image input options, two binary classifiers based on Xception and InceptionResNetV2 were trained to separate maps and pictorial maps. Results showed that the accuracy is 95-97% to distinguish maps from other images, whereas maps with pictorial objects are correctly classified at rates of 87-92%. For a third experiment, bounding boxes of 3200 sailing ships were annotated in historic maps from different digital libraries. Faster R-CNN and RetinaNet were compared to determine the box coordinates, while adjusting anchor scales and examining configurations for small objects. A resulting average precision of 32% was obtained for Faster R-CNN and of 36% for RetinaNet. Research outcomes are relevant for trawling map images on the Internet and for enhancing the advanced search of digital map catalogues.
en_US
dc.language.iso
en
en_US
dc.publisher
Taylor & Francis
en_US
dc.subject
Artificial intelligence
en_US
dc.subject
convolutional neural networks
en_US
dc.subject
pictorial maps
en_US
dc.subject
map libraries
en_US
dc.subject
classification
en_US
dc.subject
object detection
en_US
dc.title
Detection of Pictorial Map Objects with Convolutional Neural Networks
en_US
dc.type
Journal Article
dc.date.published
2020-09-11
ethz.journal.title
The Cartographic Journal
ethz.journal.volume
58
en_US
ethz.journal.issue
1
en_US
ethz.journal.abbreviated
Cartogr.J.
ethz.pages.start
50
en_US
ethz.pages.end
68
en_US
ethz.grant
Storytelling with Animated Interactive Objects in Real-time 3D Maps
en_US
ethz.identifier.wos
ethz.publication.place
London
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02115 - Dep. Bau, Umwelt und Geomatik / Dep. of Civil, Env. and Geomatic Eng.::02648 - Inst. f. Kartografie und Geoinformation / Institute of Cartography&Geoinformation::03466 - Hurni, Lorenz / Hurni, Lorenz
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02115 - Dep. Bau, Umwelt und Geomatik / Dep. of Civil, Env. and Geomatic Eng.::02648 - Inst. f. Kartografie und Geoinformation / Institute of Cartography&Geoinformation::03466 - Hurni, Lorenz / Hurni, Lorenz
ethz.grant.agreementno
ETH-11 17-1
ethz.grant.fundername
ETHZ
ethz.grant.funderDoi
10.13039/501100003006
ethz.grant.program
ETH Grants
ethz.date.deposited
2020-10-02T02:46:13Z
ethz.source
WOS
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2021-08-11T15:04:34Z
ethz.rosetta.lastUpdated
2021-08-11T15:04:34Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Detection%20of%20Pictorial%20Map%20Objects%20with%20Convolutional%20Neural%20Networks&rft.jtitle=The%20Cartographic%20Journal&rft.date=2021&rft.volume=58&rft.issue=1&rft.spage=50&rft.epage=68&rft.issn=0008-7041&1743-2774&rft.au=Schn%C3%BCrer,%20Raimund&Sieber,%20Ren%C3%A9&Schmid-Lanter,%20Jost&%C3%96ztireli,%20A.%20Cengiz&Hurni,%20Lorenz&rft.genre=article&rft_id=info:doi/10.1080/00087041.2020.1738112&
 Search print copy at ETH Library

Files in this item

FilesSizeFormatOpen in viewer

There are no files associated with this item.

Publication type

Show simple item record