Estimation of Average Vehicle Speeds Traveling on Heterogeneous Lanes Using Bluetooth Sensors

We investigate the problem of estimating the average speeds of vehicles traveling in different types of lanes, e.g., express lanes and local lanes, without knowing which lanes individual vehicles were traveling in. In our study, we use the recordings at two spatially separated Bluetooth sensors, which contain the globally unique Bluetooth device addresses of Bluetooth-enabled devices inside vehicles. These recordings are used to compute the vehicle speeds. Unfortunately, these recordings do not tell us which lanes the vehicles were traveling in and hence do not allow us to directly estimate the separate average speeds of vehicles, for example, in express lanes and local lanes or in high occupancy vehicle (HOV) lanes and regular lanes. We propose a novel estimation scheme that can provide separate average speeds of the vehicles in different types of lanes. We demonstrate the feasibility and accuracy of our proposed scheme, using real data collected by Bluetooth sensors alongside highways.