L0-Sparse DOA Estimation of Close Sources with Modeling Errors

In the field of array processing, Direction-Of-Arrival (DOA) estimation of close sources in the presence of modeling errors is a challenging problem. Indeed, the degradation of high-resolution methods on such scenario is well known and documented in the literature. This paper proposes an operational sparse L0-regularized method as an alternative. In sparse DOA estimation methods, the determination of the regularization parameter is a critical point, and it is generally empirically tuned. We first provide, in the presence of modeling errors, a theoretical statistical study to estimate the admissible range for this parameter in the presence of two incoming sources. For close sources, we therefore show that the admissible range is shortened. For an operational system, an off-line predetermination of the regularization parameter is required. We show that its selection is closely connected to the resolution limit for a given modeling error. Numerical simulations are presented to demonstrate the efficiency of the proposed implementation and its superiority in comparison with high-resolution methods.