Combining airborne images and open data to retrieve knowledge of construction sites

Construction site planning is based on both explicit knowledge, as retrieved from regulations, and implicit knowledge, arising from experience. To retrieve and formalize rules from implicit knowledge, past construction projects can be analyzed. In this paper, we present an image analysis pipeline to retrieve information on past construction sites from airborne images. We fuse machine learning based image analysis with georeferencing and openly available geospatial data to retrieve a detailed description with true dimensions of the construction site at hand.