Deep Learning and Information Geometry for Drone Micro-Doppler Radar Classification

In this work, we build dedicated learning models for micro-Doppler radar time series classification. We develop both deep temporal architectures based on time-frequency representations, and also directly study the signal's underlying statistical Gaussian process using Information Geometry on Ri...

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:
Computer architecture
Convolution
Manifolds
Neural networks
Pipelines
Radar
Time series analysis
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this work, we build dedicated learning models for micro-Doppler radar time series classification. We develop both deep temporal architectures based on time-frequency representations, and also directly study the signal's underlying statistical Gaussian process using Information Geometry on Riemannian manifolds by developing and improving symmetric positive definite (SPD) neural networks. We also propose the aggregation of all proposed models in a single, highly performing classification pipeline.
ISSN:2375-5318
DOI:10.1109/RadarConf2043947.2020.9266689