Ground target tracking of vehicles in a wireless ground sensor network

In this paper data from a wireless unattended ground sensor network is used for tracking vehicles travelling in a road network. A multiple model particle filter algorithm, taking into account the road information, is studied. The algorithm enables tracking of targets driving both on and off road. In the PF algorithm two different dynamic models, a second order linear Gaussian model and a constant velocity model, are used to represent the on and off road motion. In order to handle realistic ground target tracking scenarios, the tracking algorithm is integrated into a multiple-sensor tracking system platform which is able to handle real data from a wireless ground sensor network. The performance of the ground target tracking algorithm is evaluated using real data together with simulated data.