Learning to Detect Windows in Urban Environments
Publication from Digital
Proc. AAPR 2007, Krumbach, Austria, May 2007 , 5/2007
This work is about a novel methodology for window detection in urban environments and its multiple use in vision system applications. The presented method for window detection includes appropriate early image processing, provides a multi-scale Haar wavelet representation for the determination of image tiles which is then fed into a cascaded classifier for the task of window detection. The classifier is learned from a Gentle Adaboost driven cascaded decision tree  on masked information from training imagery and is tested towards window based ground truth information which is - together with the original building image databases- publicly available [9, 10, 12].
The experimental results demonstrate that single window detection is to a sufficient degree successful, e.g. for the purpose of building recognition, and, furthermore, that the classifier is in general capable to provide a region of interest operator for the interpretation of urban environments. The extraction of this categorical information is beneficial to index into search spaces for urban object recognition as well as aiming towards providing a semantic focus for accurate post-processing in 3D information processing systems. Targeted applications are (i) mobile services on uncalibrated imagery, e.g. for tourist guidance, (ii) sparse 3D city modeling, and (iii) deformation analysis from high resolution imagery.