Abstract One of the hardest problems for future self-driving cars is to predict hazardous situations involving pedestrians and cyclists. Human drivers solve this problem typically by having a deeper understanding of the scene. The technical equivalent of this is to provide a hazard map, which serves as a prior for self-driving cars, enabling them to adjust driving speed and processing thresholds. In this paper, we present a method to derive such a hazard map using lidar mobile mapping. Pedestrians and cyclists …