EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Generative Text-to-Image Diffusion for Automated Map Production Based on Geosocial Media Data

Alexander Dunkel, Dirk Burghardt, Madalina Gugulica

KN - Journal of Cartography and Geographic Information · 2024-03 · 74 (1) · 3-15

DOI: 10.1007/s42489-024-00159-9 ↗

Kurz gefasst

Fachartikel in der Zeitschrift KN - Journal of Cartography and Geographic Information, online erschienen am 13.02.2024. Verfasst von Alexander Dunkel und 2 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsche Forschungsgemeinschaft, Technische Universität Dresden.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The state of generative AI has taken a leap forward with the availability of open source diffusion models. Here, we demonstrate an integrated workflow that uses text-to-image stable diffusion at its core to automatically generate icon maps such as for the area of the Großer Garten, a tourist hotspot in Dresden, Germany. The workflow is based on the aggregation of geosocial media data from Twitter, Flickr, Instagram and iNaturalist. This data are used to create diffusion prompts to account for the collective attribution of meaning and importance by the population in map generation. Specifically, we contribute methods for simplifying the variety of contexts communicated on social media through spatial clustering and semantic filtering for use in prompts, and then demonstrate how this human-contributed baseline data can be used in prompt engineering to automatically generate icon maps. Replacing labels on maps with expressive graphics has the general advantage of reaching a broader audience, such as children and other illiterate groups. For example, the resulting maps can be used to inform tourists of all backgrounds about important activities, points of interest, and landmarks without the need for translation. Several challenges are identified and possible future optimizations are described for different steps of the process. The code and data are fully provided and shared in several Jupyter notebooks, allowing for transparent replication of the workflow and adoption to other domains or datasets.

Förderung

  • Deutsche Forschungsgemeinschaft
  • Technische Universität Dresden

Zitieren

APA

Dunkel, A., Burghardt, D., & Gugulica, M. (2024). Generative Text-to-Image Diffusion for Automated Map Production Based on Geosocial Media Data. KN - Journal of Cartography and Geographic Information, 74(1), 3-15. https://doi.org/10.1007/s42489-024-00159-9

Vancouver

Dunkel A, Burghardt D, Gugulica M. Generative Text-to-Image Diffusion for Automated Map Production Based on Geosocial Media Data. KN - Journal of Cartography and Geographic Information. 2024;74(1):3-15. doi:10.1007/s42489-024-00159-9

BibTeX
@article{Dunkel2024,
  author = {Dunkel, Alexander and Burghardt, Dirk and Gugulica, Madalina},
  title = {Generative Text-to-Image Diffusion for Automated Map Production Based on Geosocial Media Data},
  journal = {KN - Journal of Cartography and Geographic Information},
  year = {2024},
  volume = {74},
  number = {1},
  pages = {3--15},
  doi = {10.1007/s42489-024-00159-9}
}
Kostenlos starten →