Optimization of facade segmentation based on layout priors

Radwa Fathalla*, George Vogiatzis

*Corresponding author for this work

Research output: Chapter in Book/Published conference outputConference publication


We propose an algorithm that provides a pixel-wise classification of building facades. Building facades provide a rich environment for testing semantic segmentation techniques. They come in a variety of styles affecting appearance and layout. On the other hand, they exhibit a degree of stability in the arrangement of structures across different instances. Furthermore, a single image is often composed of a repetitive architectural pattern. We integrate appearance, layout and repetition cues in a single energy function, that is optimized through the TRW-S algorithm to provide a classification of superpixels. The appearance energy is based on scores of a Random Forrest classifier. The feature space is composed of higher-level vectors encoding distance to structure clusters. Layout priors are obtained from locations and structural adjacencies in training data. In addition, priors result from translational symmetry cues acquired from the scene itself through clustering via the α -expansion graphcut algorithm. We are on par with state-of-the-art. We are able to fine tune classifications at the superpixel level, while most methods model all architectural features with bounding rectangles.

Original languageEnglish
Title of host publicationComputer Analysis of Images and Patterns - 17th International Conference, CAIP 2017, Proceedings
EditorsM. Felsberg, A. Heyden, N. Krüger
Place of PublicationCham, CH
Number of pages12
ISBN (Electronic)978-3-319-64689-3
ISBN (Print)978-3-3196-4688-6
Publication statusPublished - 2017
Event17th International Conference on Computer Analysis of Images and Patterns, CAIP 2017 - Ystad, Sweden
Duration: 22 Aug 201724 Aug 2017

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Conference17th International Conference on Computer Analysis of Images and Patterns, CAIP 2017

Bibliographical note

© 2017 Springer Publishing.


Dive into the research topics of 'Optimization of facade segmentation based on layout priors'. Together they form a unique fingerprint.

Cite this