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

Conference paper (2021)

Authors

Luca Pallotta University of Roma Tre
Michela Cauli University of Roma Tre
Carmine Clemente University of Strathclyde
F. Fioranelli Microwave Sensing, Signals & Systems - EEMCS
Gaetano Giunta University of Roma Tre
Alfonso Farina Consultant, Selex ES (retired) Rome
Research Group
Microwave Sensing, Signals & Systems (EEMCS) (TU Delft)
Copyright: © 2021 Luca Pallotta, Michela Cauli, Carmine Clemente, F. Fioranelli, Gaetano Giunta, Alfonso Farina
DOI: https://doi.org/10.1109/MetroAeroSpace51421.2021.9511751
Image moments Micro-Doppler Automatic target recognition Hand-gesture recognition Millimeter wave radar
More Info
expand_more

Published Date

2021

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Department

Microelectronics

Research Group

Microwave Sensing, Signals & Systems

Abstract

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 these moments such as the fact that they are defined on a discrete set and hence computed without approximations, as well as the symmetry property that allows to minimize the computational time. The experiments computed on the challenging real-recorded DopNet dataset show interesting results that confirm the effectiveness of the approach.