Traffic Condition Recognition Based on Vehicle Trajectory Big Data

Abstract

The road traffic condition information include not only congestion state but also other more important traffic control information which may not reach public in time. Through analyzing floating car trajectory data, this kind of information can be recognized automatically and timely. This work first propose a difference-based algorithm to filter the outlier trajectory data. Then present map matching method based on three-level grid which is the key to most application of floating car trajectory data. Finally we propose an automatic algorithm to recognize the road traffic control information in real time. The entire floating trajectory data of Fuzhou about 1.5 million records are used to verify the proposed method. Experiment result indicate that the method have high efficiency and accuracy rate.