• DOI:10.1145/3474717.3483650
• Corpus ID: 228064205

Route Reconstruction from Traffic Flow via Representative Trajectories

@article{Custers2020RouteRF,
  title={Route Reconstruction from Traffic Flow via Representative Trajectories},
  author={Bram Custers and Wouter Meulemans and Bettina Speckmann and Kevin Verbeek},
  journal={Proceedings of the 29th International Conference on Advances in Geographic Information Systems},
  year={2020}
}

• B. Custers, Wouter Meulemans, +1 author Kevin Verbeek
• Published 9 December 2020
• Computer Science
• Proceedings of the 29th International Conference on Advances in Geographic Information Systems

Understanding human mobility patterns is an important aspect of traffic analysis and urban planning. Trajectory data provide detailed views on specific routes, but typically do not capture all traffic. On the other hand, loop detectors built into the road network capture all traffic flow at specific locations, but provide no information on the individual routes. Given a set of loop-detector measurements as well as a (small) set of representative trajectories, our goal is to investigate how one can effectively combine these two partial data sources to create a more complete picture of the underlying mobility patterns. Specifically, we want to reconstruct a realistic set of routes from the loop-detector data, using the given trajectories as representatives of typical behavior. We model the loop-detector data as a network flow field that needs to be covered by the reconstructed routes and we capture the realism of the routes via the strong Fréchet distance to the representative trajectories. We prove that several forms of the resulting algorithmic problem are NP-hard. Hence we explore heuristic approaches which decompose the flow well while following the representative trajectories to varying degrees. We propose an iterative Fréchet Routes (FR) heuristic which generates candidates routes with bounded Fréchet distance to the representative trajectories. We also describe a variant of multi-commodity min-cost flow (MCMCF) which is only loosely coupled to the trajectories. We perform an extensive experimental evaluation of our two proposed approaches in comparison to a global min-cost flow (GMCF), which is essentially agnostic to the representative trajectories. To make meaningful claims in terms of quality, we derive a ground truth by map-matching real-world trajectories. We find that GMCF explains the flow best, but produces a large number of often nonsensical routes (significantly more than the ground truth). MCMCF produces a large number of mostly realistic routes which explain the flow reasonably well. In contrast, FR produces much smaller sets of realistic routes which still explain the flow well, at the cost of a higher running time. Finally, we report on the results of a case study which combines real-world loop detector data and representative trajectories for the region around The Hague, the Netherlands.