Joint sensors-sources association and tracking under a power constraint

This work considers the problem of tracking multiple sources using observations acquired at spatially scattered sensors and under power constraints. The Kaiman filtering minimization formulation is extended with norm-one regularization terms and a power constraint. The resulting minimization formulation is capable to associate sources with sensors, and track the unknown sources while adhering to the communication power constraint imposed across sensors. Coordinate descent techniques are used to recover the unknown sparse observation matrix, select pertinent sensors and subsequently obtain source state estimates. Numerical tests demonstrate the potential of the novel approach to identify the source-informative sensors and accurately track the field sources.