Three Rapid Methods for Averaging GPS Segments

Abstract

Extracting road segments by averaging GPS trajectories is very challenging. Most existing averaging strategies suffer from high complexity, poor accuracy, or both. For example, finding the optimal mean for a set of sequences is known to be NP-hard, whereas using Medoid compromises the quality. In this paper, we introduce three extremely fast and practical methods to extract the road segment by averaging GPS trajectories. The methods first analyze three descriptors and then use either a simple linear model or a more complex curvy model depending on an angle criterion. The results provide equal or better accuracy than the best existing methods while being very fast, and are therefore suitable for real-time processing. The proposed method takes only 0.7% of the computing time of the best-tested baseline method, and the accuracy is also slightly better (62.2% vs. 61.7%).