A novel clustering algorithm of extracting road network from low-frequency floating car data

Keeping the digital road maps up-to-date is of critical importance, because the quality of many road-dependent services relies on it, but traditional measurement methods are still time-consuming and expensive. With the GPS technology and wireless communication technology maturing, the positioning data from floating car become a new data source for updating road maps. The paper presents a novel incremental clustering algorithm for automatically extracting the topology of the road network employing the floating car data. A trajectory is selected as a road Link and then the remaining trajectories are added in turn until all tracks are processed. Further, the algorithm determines whether to merge the trajectory or divide it into a new Link by judging the relations of the space position between the newly added trajectory and the existing Link. A partial curve matching method based on Fréchet distance is employed to measure the partial similarity between a Trajectory and a Link and the time complexity of the proposed algorithm is reduced. Experiments show that the algorithm can quickly extract the geometric shape and topology of the road network with lightweight floating car data.