Learning cartographic building generalization with deep convolutional neural networks

Download statistics - Document (COUNTER):

Feng, Y.; Thiemann, F.; Sester, M.: Learning cartographic building generalization with deep convolutional neural networks. In: ISPRS International Journal of Geo-Information 8 (2019), Nr. 6, 258. DOI: https://doi.org/10.3390/ijgi8060258

Repository version

To cite the version in the repository, please use this identifier: https://doi.org/10.15488/8808

Selected time period:


Sum total of downloads: 196

Cartographic generalization is a problem, which poses interesting challenges to automation. Whereas plenty of algorithms have been developed for the different sub-problems of generalization (e.g., simplification, displacement, aggregation), there are still cases, which are not generalized adequately or in a satisfactory way. The main problem is the interplay between different operators. In those cases the human operator is the benchmark, who is able to design an aesthetic and correct representation of the physical reality. Deep learning methods have shown tremendous success for interpretation problems for which algorithmic methods have deficits. A prominent example is the classification and interpretation of images, where deep learning approaches outperform traditional computer vision methods. In both domains-computer vision and cartography-humans are able to produce good solutions. A prerequisite for the application of deep learning is the availability of many representative training examples for the situation to be learned. As this is given in cartography (there are many existing map series), the idea in this paper is to employ deep convolutional neural networks (DCNNs) for cartographic generalizations tasks, especially for the task of building generalization. Three network architectures, namely U-net, residual U-net and generative adversarial network (GAN), are evaluated both quantitatively and qualitatively in this paper. They are compared based on their performance on this task at target map scales 1:10,000, 1:15,000 and 1:25,000, respectively. The results indicate that deep learning models can successfully learn cartographic generalization operations in one single model in an implicit way. The residual U-net outperforms the others and achieved the best generalization performance.
License of this version: CC BY 4.0 Unported
Document Type: article
Publishing status: publishedVersion
Issue Date: 2019
Appears in Collections:Fakultät für Bauingenieurwesen und Geodäsie

distribution of downloads over the selected time period:

downloads by country:

pos. country downloads
total perc.
1 image of flag of Germany Germany 77 39.29%
2 image of flag of United States United States 18 9.18%
3 image of flag of France France 8 4.08%
4 image of flag of United Kingdom United Kingdom 7 3.57%
5 image of flag of Hong Kong Hong Kong 6 3.06%
6 image of flag of Russian Federation Russian Federation 5 2.55%
7 image of flag of Sri Lanka Sri Lanka 4 2.04%
8 image of flag of India India 4 2.04%
9 image of flag of Spain Spain 4 2.04%
10 image of flag of Czech Republic Czech Republic 4 2.04%
    other countries 59 30.10%

Further download figures and rankings:


Zur Erhebung der Downloadstatistiken kommen entsprechend dem „COUNTER Code of Practice for e-Resources“ international anerkannte Regeln und Normen zur Anwendung. COUNTER ist eine internationale Non-Profit-Organisation, in der Bibliotheksverbände, Datenbankanbieter und Verlage gemeinsam an Standards zur Erhebung, Speicherung und Verarbeitung von Nutzungsdaten elektronischer Ressourcen arbeiten, welche so Objektivität und Vergleichbarkeit gewährleisten sollen. Es werden hierbei ausschließlich Zugriffe auf die entsprechenden Volltexte ausgewertet, keine Aufrufe der Website an sich.

Search the repository