Daniel Zaum

Improving GPS-based road network constructions in a post-processing step of global optimization

Since digital maps of high spatial and temporal resolution and precision are widely regarded as key enabler for advanced driver assistance systems and automated driving, the research field of automated map generation from crowd-sourced fleet data has gained importance in recent years. This paper proposes a novel optimization method for improving the results of known road-network construction algorithms in a post-processing step. The method is proven to be feasible by an evaluation of the results on real-world datasets. Furthermore, the applicability to traditional GPS data is explored.

Road network reconstruction using reversible jump MCMC simulated annealing based on vehicle trajectories from fleet measurements

Being regarded as essential for advanced driver assistance systems and autonomous driving, the research field of map generation from crowd-sourced vehicle information gained attention in the last decade. This paper introduces a novel approach for the derivation of street accurate road networks from such data. The method is applied to a real-world dataset of different accuracy level and is evaluated against a ground truth map. Furthermore, the results are compared to results of two state of the art algorithms.