Abstract
Map-matching is a process that aligns location points on a digital map and it is an essential step in location-based services. However, regular map-matching methods cannot archive very high accuracy due to the errors in raw location data and the complexity of road networks. Hence, the final resort for map matching is often through manual annotation, which is human labour intensive. Therefore, we propose iMatching, an interactive system for map-matching which greatly reduces annotation cost and achieves a high accuracy through an active learning approach. Specifically, we model the mapping of a sequence of location points to a road network as a hidden Markov model and automatically generate an initial result. Then, we select error-prone points on the trajectory and guide the annotator to review, and possibly correct, the results. Our evaluation on both real-world and synthetic data demonstrates that iMatching has a better performance comparing with the existing methods.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have