Rapid traffic congestion monitoring based on floating car data

Floating car technology is the essential source to acquire the road traffic information in intelligent transportation systems. It can be used as the data source for large-scale real-time traffic monitoring. It's a challenge of handling stream data effectively in a large number of moving objects because of the huge scale of (floating car data, FCD). In this paper, a congestion companion discovery algorithm is proposed by adopting the idea of similar trajectory clustering and utilizing traffic parameters with congestion characteristics. The candidate congestion FCD can be filtered out from the floating car trajectory stream for approximately predicting the trend of congestion areas. While the load shedding decision-making is determined by the prediction, an algorithm of multi-priority scheduling based on prediction is designed to achieve the whole monitoring process. Our method can effectively reduce the processing cost of FCD, and rapidly monitor traffic congestion. Both efficiency and effectiveness of our method are evaluated by a very large volume of real taxi trajectories in an urban road network.