Online Freeway Traffic Estimation with Real Floating Car Data

In this paper, the performance of the well-known Generalized Adaptive Smoothing Method (GASM) as online traffic speed estimator with Floating Car Data (FCD) as single source of data is assessed. Therefore, the main challenges originating from the sparseness and delay in collecting FCD are addressed and a procedure using the GASM is proposed that allows estimating traffic velocities continuously. In a subsequent study, the method is applied to real FCD recorded by a huge fleet of privacy-aware mobile sensors during a common congestion pattern on German freeway A99. Focus of the study is to assess the accuracy of traffic speed estimation using the online GASM with respect to varying data densities and delays. The result is that the proposed estimator outperforms naïve approaches in almost all considered setups. Significant accuracy gains compared to naïve methods are achieved, especially if the parameter sets are chosen according to the characteristics of given data. Yet, insufficient actuality of data challenges the GASM, revealing new potential for further enhancements of the method.