Jan Winkler
Loading...
1 results
Filters
Reset filtersSearch Results
Publications 1 - 1 of 1
- Progress in Constructing an Open Map Generalization Data Set for Deep LearningItem type: Conference Paper
Leibniz International Proceedings in Informatics (LIPIcs) ~ 12th International Conference on Geographic Information Science (GIScience 2023)Fu, Cheng; Zhou, Zhiyong; Winkler, Jan; et al. (2023)Recent pioneering works have shown the potential of a new deep-learning-backed paradigm for automated map generalization. However, this approach also puts a high demand on the availability of balanced and rich training sets. We present our design and progress of constructing an open training data set that can support relevant studies, collaborating with the Swiss Federal Office of Topography. The proposed data set will contain transitions of building and road generalization in Swiss maps at 1:25k, 1:50k, and 1:100k. By analyzing the generalization operators involved in these transitions, we also propose several challenges that can benefit from our proposed data set. Besides, we hope to also stimulate the production of further open data sets for deep-learning-backed map generalization.
Publications 1 - 1 of 1