Analysis of U-NET Super-Resolving Capabilities in Radar Imaging

This article investigates the super-resolving power of U-NET when applied to a radar imaging problem. In particular, we consider a 2-D free-space scenario probed by a multimonostatic/multifrequency measurement configuration and formulate the imaging problem as a linear inverse scattering one. In this context, we analyze how the degree of ill-posedness of the inverse problem affects the resolution limits achievable by the U-NET. To this aim, the system point spread function (PSF), i.e., the reconstruction of a point-like target, is evaluated via the classical truncated singular value decomposition (TSVD) and used as input to the network. Numerical results relevant to different configuration parameters confirm the “super-resolving” capability of the network, but the achievable performance turns out to be strongly dependent on the amount of information in the scattered field data.