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

Abstract

Undocumented building constructions are buildings or stories that were built years ago,but are missing in the official digital cadastral maps (DFK). The detection of undocumented buildingconstructions is essential to urban planning and monitoring. The state of Bavaria, Germany, uses twosemi-automatic detection methods for this task that suffer from a high false alarm rate. To solve thisproblem, we propose a novel framework to detect undocumented building constructions using aConvolutional Neural Network (CNN) and official geodata, including high resolution optical dataand the Normalized Digital Surface Model (nDSM). More specifically, an undocumented buildingpixel is labeled as “building” by the CNN but does not overlap with a building polygon of the DFK.The class of old or new undocumented building can be further separated when a Temporal DigitalSurface Model (tDSM) is introduced in the stage of decision fusion. In a further step, undocumentedstory construction is detected as the pixels that are “building” in both DFK and predicted resultsfrom CNN, but shows a height deviation from the tDSM. By doing so, we have produced a seamlessmap of undocumented building constructions for one-quarter of the state of Bavaria, Germany at aspatial resolution of 0.4 m, which has proved that our framework is robust to detect undocumentedbuilding constructions at large-scale. Considering that the official geodata exploited in this researchis advantageous because of its high quality and large coverage, a transferability analysis experimentis also designed in our research to investigate the sampling strategies for building detection atlarge-scale. Our results indicate that building detection results in unseen areas at large-scale can beimproved when training samples are collected from different districts. In an area where trainingsamples are available, local training sampless collection and training can save much time and effort.