Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XXXVIII-5/W16, 171-176, 2011
© Author(s) 2011. This work is distributed
under the Creative Commons Attribution 3.0 License.
10 Sep 2012
M. Mathias1, A. Martinovic1, J. Weissenberg2, S. Haegler2, and L. Van Gool1,2 1PSI/VISICS, Department of Electrical Engineering, KU Leuven, Kasteelpark Arenberg 10/02441, 3001 Heverlee, Belgium
2Computer Vision Laboratory, ETH Zurich, Sternwartstrasse 7, 8092 Zurich, Switzerland
Keywords: procedural modeling, architectural styles, scene classification, gist, facades, supervised learning Abstract. Procedural modeling has proven to be a very valuable tool in the field of architecture. In the last few years, research has soared to automatically create procedural models from images. However, current algorithms for this process of inverse procedural modeling rely on the assumption that the building style is known. So far, the determination of the building style has remained a manual task. In this paper, we propose an algorithm which automates this process through classification of architectural styles from facade images. Our classifier first identifies the images containing buildings, then separates individual facades within an image and determines the building style. This information could then be used to initialize the building reconstruction process. We have trained our classifier to distinguish between several distinct architectural styles, namely Flemish Renaissance, Haussmannian and Neoclassical. Finally, we demonstrate our approach on various street-side images.
Conference paper (PDF, 6368 KB)

Citation: Mathias, M., Martinovic, A., Weissenberg, J., Haegler, S., and Van Gool, L.: AUTOMATIC ARCHITECTURAL STYLE RECOGNITION, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XXXVIII-5/W16, 171-176, doi:10.5194/isprsarchives-XXXVIII-5-W16-171-2011, 2011.

BibTeX EndNote Reference Manager XML