A Hermitian Positive Definite neural network for micro-Doppler complex covariance processing

In its raw form, micro-Doppler radar data takes the form of a complex time-series, which can be seen as multiple realizations of a Gaussian process. As such, a complex covariance matrix constitutes a viable and synthetic representation of such data. In this paper, we introduce a neural network on He...

Full description

Saved in:
Bibliographic Details
Main Authors: Brooks, Daniel, Schwander, Olivier, Barbaresco, Frederic, Schneider, Jean-Yves, Cord, Matthieu
Format: Conference Proceeding
Language:English
Subjects:
Blades
complex numbers
Conferences
Covariance matrices
drone classification
Drones
Manifolds
micro-Doppler
Neural networks
Radar
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In its raw form, micro-Doppler radar data takes the form of a complex time-series, which can be seen as multiple realizations of a Gaussian process. As such, a complex covariance matrix constitutes a viable and synthetic representation of such data. In this paper, we introduce a neural network on Hermitian Positive Definite (HPD) matrices, that is complex-valued Symmetric Positive Definite (SPD) matrices, or complex covariance matrices. We validate this new architecture on synthetic data, comparing against previous similar methods.
ISSN:2640-7736
DOI:10.1109/RADAR41533.2019.171277