Obtaining structural descriptions of building façades
Petar Vračar, Igor Kononenko, Marko Robnik‐Šikonja · Computer Science and Information Systems · 2015
We describe a method for learning and recognizing windows as basic structural elements of fa?ades and organizing them into interpretable models of building fa?ades. The method segments an input image into a hierarchical structure of window candidates. The candidates are used to create a likelihood map of window locations that is explained by a structural fa?ade model based on a formal grammar. We use a look-ahead greedy search method in the grammar derivation space to select the (sub)optimal fa?ade model. Empirical evaluation results reveal that, on average, the generated fa?ade model covers 45% of the actual windows present in the input image. On the other hand, 56% of the modeled windows actually cover fa?ade windows present in the input image.