Non-Supervised High Resolution Doppler Machine Learning for Pathological Radar Clutter
Language
en
Communication dans un congrès
This item was published in
2019 International Radar Conference (RADAR), 2019 International Radar Conference (RADAR), RADAR 2019, 2020-09-23, Toulon.
English Abstract
In this paper we propose a method to classify radar clutter from radar data using a non-supervised classification algorithm. As a final objective, new radars will therefore be able to use the experience of other radars to ...Read more >
In this paper we propose a method to classify radar clutter from radar data using a non-supervised classification algorithm. As a final objective, new radars will therefore be able to use the experience of other radars to improve their performances: learning pathological radar clutter can be used to fix some false alarm rate created by strong echoes coming from hail, rain, waves, mountains, cities; it will also improve the detectability of slow moving targets, like drones, which can be hidden in the clutter, flying close to the landform.Read less <
English Keywords
non-supervised classification
machine learning
radar clutter
k-means
autocorrelation matrix
Burg algorithm
reflection coefficients
Kähler metric
Origin
Hal imported