Material determination from reflectance properties in aerial urban images

Telecommunication operators intensively use simulation tools for optimizing positioning in mobile communication networks. These simulators are based on digital surface models to estimate electromagnetic wave propagation. In addition to a three dimensional model of the city which is conveniently obtained from aerial images, we propose to establish a cartography of urban materials from the same data. This cartography is derived from an analysis of the BRDF (binomial reflectivity distribution) of the materials under different viewing angles. For this purpose, we use a simple light reflection model and for each building or terrain parcel, we determine the parameters of the model. We found experimentally that the Blinn's model, although not physically derived, is the most adequate for this application. We propose to use a robust estimation method, the least median of squares estimator on Blinn's model. We test it on various materials, like red and dark tiles and slates. Calculated parameters are evaluated according to assumptions made on surface quality of these materials. We present the limits of the method.