A vehicle tracking method includes receiving distributed optical fiber sensing (DFOS) data. The vehicle tracking method includes identifying hit points within the DFOS data, wherein each of the hit points corresponds to a location of a corresponding vehicle at a detection time. The vehicle tracking method includes clustering the identified hit points to define one or more clusters. The vehicle tracking method includes classifying each of the one or more clusters into a first or second classification based on a quantity of the hit points in each of the one or more clusters and a quantity of the detection times. The vehicle tracking method includes estimating a vehicle parameter of a first vehicle corresponding to the hit points of a first cluster of the one or more clusters, wherein the first cluster has the first classification, and the estimating is based on the hit points of the first cluster.