We first address vehicle classification and tracking problems using acoustic, video, and radar sensors. We formulate solutions for joint acoustic-video and acoustic-radar target tracking problems with particle filters. Each joint tracker incorporates target acoustic propagation delays for robust operation. For classification, we determine a vehicle’s speed, width, and length by jointly estimating its acoustic wave-pattern using a single passive acoustic sensor that records the vehicle’s drive-by noise. We further improve the acoustic classification results with video mensuration.

We then investigate an optimal resource allocation problem for sensor networks with limited connectivity. Our focus is the network build strategy, where we determine the number of sensors of different types to deploy from a sensor pool that offers a distinct cost vs. performance trade-off for each type of sensor. For generality, we consider randomly deployed sensor networks and formulate constrained optimization techniques in a Bayesian experimental design framework to obtain the best knowledge about a given state-of-nature represented by a finite number of parameters, and to make the optimal decisions for statistical classification problems based on the Neyman-Pearson fundamental lemma. We illustrate the results by designing an acoustic sensor network for vehicle position tracking.