DipSAR: Deep Image Prior for Sparse Sampled Near-Field SAR Millimeter-Wave Imaging

We present a deep learning-based approach called DipSAR for reconstructing millimeter-wave synthetic aperture radar (SAR) images from sparse samples. The primary challenge lies in the requirement of a large training dataset for deep learning schemes. To overcome this issue, we employ the deep image prior (DIP) technique, which eliminates the...

Classification of micro-Doppler radar hand-gesture signatures by means of Chebyshev moments

In this paper a method capable of automatically classify radar signals of human hand-gestures exploiting the micro-Doppler signature is designed. In particular, the methodology focuses on the extraction of the Chebyshev moments from the cadence velocity diagram (CVD) of each recorded signal. The algorithm benefits from interesting properties of...