Fast Online Map Matching for Recovering Travelling Routes from Low-Sampling GPS Data

Abstract

With the widespread use of mobile and sensor devices, a large amount of GPS data has been generated. To gain deep understanding of human mobility in cities, it is essential to recover the travelling route from these low-sampling and noisy GPS data. In this paper, an online map matching algorithm is proposed for inferring the travelling routes from the low-sampling GPS data in real-time. Unlike the existing online map matching methods which often experience an inference delay between the observation and inference, our algorithm can produce immediate inference when a new GPS point becomes available. In addition, a rollback mechanism is provided to correct the already inferred route when some unusual conditions are detected. It helps to ensure the inference accuracy especially for online inference. We evaluate the proposed algorithm using real dataset of GPS trajectories over 100 cities around the world. Experimental results show that our algorithm outperforms the existing algorithms in terms of both inference accuracy and efficiency.