Deep learning in historical geography

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21110%2F24%3A00376355" target="_blank" >RIV/68407700:21110/24:00376355 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.13164/juniorstav.2024.24097" target="_blank" >https://doi.org/10.13164/juniorstav.2024.24097</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.13164/juniorstav.2024.24097" target="_blank" >10.13164/juniorstav.2024.24097</a>

Result language
angličtina
Original language name
Deep learning in historical geography
Original language description
In relation to the rapid development of artificial intelligence, the possibilities of automatic processing of spatial data are increasing. Scanned topographical maps are a valued source of historical information. Neural networks allow us to extract information quickly and efficiently from such data, eliminating the difficult and repetitive work that would otherwise have to be done by a human. The article presents two case studies exploring the possibilities of using deep learning in historical geography. The first one is concerned with detecting and extracting swamps from topographic maps, while the second one attempts to automatically vectorize contours from the State Map 1 : 5 000.
Czech name
—
Czech description
—

Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Juniorstav 2024: Proceedings 26th International Scientific Conference Of Civil Engineering
ISBN
978-80-86433-83-7
ISSN
3029-5904
e-ISSN
3029-5904
Number of pages
5
Pages from-to
—
Publisher name
Brno University of Technology
Place of publication
Brno
Event location
Brno
Event date
Jan 25, 2024
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)