The following paper has been presented at the 25th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems: K. Buchin, M. Buchin, D. Duran, B.T. Fasy, R. Jacobs, V. Sacristan, R. Silveira, F. Staals, C. Wenk. Clustering Trajectories for Constructing Maps. ACM SIGSPATIAL GIS 2017.
The paper presents a new approach for constructing the underlying map from trajectory data. The algorithm is based on the idea that road segments can be identified as stable subtrajectory clusters in the data. As subtrajectory clusters evolve for varying distance values, stable values for distance values are extracted. This avoids apriori knowledge of a global proximity parameter. Experiments were performed on vehicle and hiking tracking data, and they show that this new approach can naturally separate roads that run close to each other and can deal with outliers in the data, two issues that are notoriously difficult in road network reconstruction.