Review & Perspective for Distance Based Clustering of Vehicle Trajectories

Philippe Besse (1) , Brendan Guillouet (1) , Jean-Michel Loubes (1) , François Royer (2)

1 IMT - Institut de Mathématiques de Toulouse UMR5219
2 Datasio

—In this paper we tackle the issue of clustering trajectories of geolocalized observations based on distance between trajectories. We first provide a comprehensive review of the different distances used in the literature to compare trajectories. Then based on the limitations of these methods, we introduce a new distance: Symmetrized Segment-Path Distance (SSPD). We compare this new distance to the others according to their corresponding clustering results obtained using both the hierarchical clustering and affinity propagation methods. We finally present a python package : trajectory distance, which contains the methods for calculating the SSPD distance and the other distances reviewed in this paper.

Domaines: Applications [stat.AP]

Philippe Besse, Brendan Guillouet, Jean-Michel Loubes, François Royer. Review & Perspective for Distance Based Clustering of Vehicle Trajectories. IEEE Transactions on Intelligent Transportation Systems, 2016, 17 (11), pp.3306-3317. ⟨10.1109/TITS.2016.2547641⟩. ⟨hal-01305993⟩