Computational & Technology Resources
an online resource for computational,
engineering & technology publications
engineering & technology publications
Civil-Comp Conferences
ISSN 2753-3239
ISSN 2753-3239
CCC: 11
PROCEEDINGS OF THE SEVENTH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, SOFT COMPUTING, MACHINE LEARNING AND OPTIMIZATION IN ENGINEERING
PROCEEDINGS OF THE SEVENTH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, SOFT COMPUTING, MACHINE LEARNING AND OPTIMIZATION IN ENGINEERING
Edited by: P. Iványi, J. Kruis and B.H.V. Topping
Paper 1.3
Deep Learning Methods for the Analysis of Townscapes
S. Balestra1, O. Hänni2, M.-A. Iten3, M. Blöchlinger2, S. Bühler-Krebs2 and R.-P. Mundani1
1Institute for Data Analysis, Artificial Intelligence, Visualization and Simulation (DAViS), University of Applied Sciences of the Grisons, Chur, Switzerland
2Institute for Construction in Alpine Regions (IBAR), University of Applied Sciences of the Grisons, Chur, Switzerland
3Swiss Institute for Information Science (SII), University of Applied Sciences of the Grisons, Chur, Switzerland
Full Bibliographic Reference for this paper
S. Balestra, O. Hänni, M.-A. Iten, M. Blöchlinger, S. Bühler-Krebs, R.-P. Mundani, "Deep Learning Methods for the Analysis of Townscapes", in P. Iványi, J. Kruis, B.H.V. Topping, (Editors), "Proceedings of the Seventh International Conference on
Artificial Intelligence, Soft Computing, Machine Learning and Optimization in Engineering", Civil-Comp Press, Edinburgh, UK,
Online volume: CCC 11, Paper 1.3, 2025,
Keywords: artificial intelligence, deep learning, architecture, urban development, building culture, semantic segmentation.
Abstract
Finding architectural principles in facades is an important task for urban development. Hence, using AI-based methods for an automated analysis seems obvious, but this also entails certain requirements concerning the training data itself. A new facade dataset with 14 segmentation masks was created and used for the training of deep learning models to semantically segment elements within facades of Swiss buildings. Via a rule-based approach, architectural principles such as rhythm lines and axes of symmetry can be derived from these elements. Those principles, especially in the context of neighbouring buildings, form an architectural pattern that is partially quantifiable to assure quality in design w. r. t. urban development.
download the full-text of this paper (PDF, 9309 Kb)
go to the previous paper
go to the next paper
return to the table of contents
return to the volume description