Formalizing expert knowledge for building information models: Automated identification of electrical wiring from 3d scans

New computational methods provide means to deduce semantic information from measurements, such as range scans and photographs of building interiors. In this paper, we showcase a method that allows to estimate elements that are not directly observable – ducts and power lines in walls. For this, we combine explicit information, which is deducted by algorithms from the raw data, with implicit information that is publicly available: technical standards that restrict the placement of powerlines.
We present a complete pipeline from measurements to power line hypothesis. The approach is structured into the following steps: First, a coarse geometry is extracted from input measurements; i.e. the unstructured, laser-scanned point cloud is transformed into a simplistic building model. Then, visible endpoints of electrical appliances (e.g. sockets, switches) are detected from picture information using machine-learning techniques and a pre-trained classifier. Afterwards, the positions of installation zones in walls are generated using the implicit knowledge. Finally, a hypothesis of non-visible cable ducts is generated, under the assumption that (i) the real configuration obeys the rules of legal requirements and standards and (ii) the configuration connects all endpoints using as little as possible resources, i.e. cable length.