Automated Classification of Building Roofs for the Updating of 3D Building Models Using Heuristic Methods

Abstract

In the Bavarian Surveying Administration, remote sensing methods are applied in the context of nationwide airborne surveys for the acquisition of aerial photographs and airborne laser scanning for the derivation of the digital terrain model (DTM). At the Bavarian Agency for Digitisation, High-Speed Internet and Surveying (LDBV = Landesamt für Digitalisierung, Breitband und Vermessung), image-based digital surface models (bDOM) and digital orthophotos without building lean (trueDOP) are produced using the dense image matching (DIM) method. Buildings and their roofs are displayed in the trueDOP in the correct position to the cadastral ground plan. Based on these data, an expert system was developed for the investigation of construction cases and for the updating of 3D building models, which automatically calculates change notices and makes them available to the Agencies for Digitisation, High-Speed Internet and Surveying (ADBV = Amt für Digitalisierung, Breitband und Vermessung). The reliable detection of buildings plays a decisive role here. Representative reference classes for the classification of building roofs in the RGB colour space are formed and frequencies are calculated across the boundaries of the photo-flights. The classification is carried out with the aid of a normalized digital surface model (nDOM), which is calculated from the height differences between the bDOM and the DTM, and with heuristically defined threshold values for the colours in the representative RGB colour spaces. The presented method is transferable to all federal states.

Detection of Undocumented Building Constructions from Official Geodata Using a Convolutional Neural Network

“…In the state of Bavaria, Germany, there are two conventional strategies utilized to detect undocumented buildings, the filter-based method [3] and the comparison-based method [4]. For both methods, the detection of undocumented buildings is carried out by first detecting all buildings in the remote sensing data and then identifying undocumented buildings within the DFK by overlaying the results with the DFK.…”

“…The building footprints from the DFK are first intersected with the TrueDOP to derive the training areas of buildings. Then, the RGB color values from the training areas are collected from the TrueDOP as a reference [4], where the frequency and distribution of the individual RGB combination are utilized in order to separate buildings from vegetation with an empirically chosen threshold. Finally, with the help of the nDSM, incorrect classifications between buildings and other objects such as streets are avoided by an empirically determined height threshold.…”

“…In order to reduce the amount of work, two semi-automatic strategies are currently used by the state of Bavaria, Germany for the detection of undocumented buildings: the filter-based method [3] and the comparison-based method [4]. Both of these methods first detect buildings in remote sensing data.…”