Learning Domain Knowledge for Facade Labelling

This paper presents an approach to address the problem of image facade labelling. In the architectural literature, domain knowledge is usually expressed geometrically in the final design, so facade labelling should on the one hand conform to visual evidence, and on the other hand to the architectural principles - how individual assets (e. g. doors, windows) interact with each other to form a facade as a whole. To this end, we first propose a recursive splitting method to segment facades into a bunch of tiles for semantic recognition. The segmentation improves the processing speed, guides visual recognition on suitable scales and renders the extraction of architectural principles easy. Given a set of segmented training facades with their label maps, we then identify a set of meta-features to capture both the visual evidence and the architectural principles. The features are used to train our facade labelling model. In the test stage, the features are extracted from segmented facades and the inferred label maps. The following three steps are iterated until the optimal labelling is reached: 1) proposing modifications to the current labelling; 2) extracting new features for the proposed labelling; 3) feeding the new features to the labelling model to decide whether to accept the modifications. In experiments, we evaluated our method on the ECP facade dataset and achieved higher precision than the state-of-the-art at both the pixel level and the structural level.