Robust Target Classification Using UWB Sensing

BOUZA, MAGDALENA; ALTIERI, ANDRÉS; GALARZA, CECILIA G.

IEEE Access

IEEE

Año: 2023 vol. 11 p. 44267 - 44277

Contactless material characterization has received widespread attention in the radar and engineering domain. Specifically, impulsive Ultra Wideband (UWB) systems are a versatile technology for the non-destructive characterization of samples because the scattered field produced by the targets is highly dependent on their composition and shape. After the initial transient response to the transmitted pulse, the scattered signal can be decomposed as a sum of complex exponentials, called the complex natural resonances (CNR), which are dependent only upon the geometry and composition of the target. Using this result, we formulate a classification problem to discriminate among targets, and we propose a processing strategy to solve it. In particular, using spectral decomposition tools, we exploit the information obtained from the physical model in combination with data-driven learning techniques. As a result, we design a classification strategy that is robust under modeling uncertainties and experimental perturbations. To assess the performance of the new scheme, we test it both with synthetic data and with experimental data obtained from targets illuminated with an UWB radar. The results show substantial gains compared to performing the classification using time-domain signals.