Interactive detection of 3D models of building's roofing for the estimation of the solar energy potential

The paper presents the work in progress of the design and implementation of an interactive system for the detection of the building's roofing characteristic. For each of its pitches data concerning height, shape, orientation, slope and useful area are estimated at different precision levels. The system operates on a cartographic map and two pre-processed aerial photographs that are aligned for building selection, image segmentation and 3D modelling. Each building roofing is automatically classified and its features are used for disparity computation from two stereoscopic views for precise 3D modelling. Different disparity measurement algorithms are being experimented to measure their accuracy based on reference test buildings. The 3D model is the input to standard software packages for solar energy potential estimation.