Assessing Completeness of OpenStreetMap Building Footprints Using MapSwipe

Natural hazards threaten millions of people all over the world. To address this risk, exposure and vulnerability models with high resolution data are essential. However, in many areas world, rather coarse aggregated large areas. Although OpenStreetMap (OSM) offers great potential to assess risk at a detailed building-by-building level, completeness OSM building footprints is still heterogeneous. We present an approach close gap by means crowd-sourcing based on mobile app MapSwipe, where volunteers swipe through satellite images region collecting user feedback classification tasks. For our application, MapSwipe was extended feature that allows classify tile as “no building”, “complete” or “incomplete”. quality produced data, applied four regions. The MapSwipe-based assessment compared intrinsic quantify prediction existing model. Our results show crowd-sourced yields reasonable performance footprints. Results showed consistent estimates for case study regions while other two approaches higher variability. also revealed tend nearly completely mapped tiles “complete”, especially density. Another factor influenced level alignment layer imagery.