A ST-CRF Map-Matching Method for Low-Frequency Floating Car Data

Integrating raw Global Position System (GPS) trajectories with a road network is often referred to as a map-matching problem. However, low-frequency trajectories (e.g., one GPS point for every 1–2 min) have raised many challenges to existing map-matching methods. In this paper, we propose a novel and global spatial–temporal map-matching method called spatial and temporal conditional random field (ST-CRF), which is based on insights relating to: 1) the spatial positioning accuracy of GPS points with the topological information of the underlying road network; 2) the spatial–temporal accessibility of a floating car; 3) the spatial distribution of the middle point between two consecutive GPS points; and 4) the consistency of the driving direction of a GPS trajectory. We construct a conditional random field model and identify the best matching path sequence from all candidate points. A series of experiments conducted for real environments using mass floating car data collected in Beijing and Shanghai shows that the ST-CRF method not only has better performance and robustness than other popular methods (e.g., point-line, ST-matching, and interactive voting-based map-matching methods) in low-frequency map matching but also solves the “label-bias” problem, which has long existed in the map matching of classical hidden Markov-based methods.