Interpretation of mobile mapping data for the creation and update of spatial databases of the public domain

During a construction project on the public domain there are many different stakeholders who have to cooperate. To ensure this, a centralized reference database is needed. For this we have the GRB in Flanders, a spatial database which is used as reference for all project plans. Having such an important role, it is essential to keep the GRB up to date. The objective of this research project is to automatically create and update these spatial databases using mobile mapping data. This research project will investigate the use of cutting edge object detection and machine learning algorithms on imagery and LIDAR data from state of the art mobile mapping systems. This will result in an automated workflow for the creation of as-built maps used to create or update spatial databases and an error detection system to check existing databases. In addition, a later part will focus on the improvement of the data accuracy of low-end mobile mapping systems so they can be deployed for these mapping purposes.