Title :
Geometric Radar Processing based on Fréchet distance: Information geometry versus Optimal Transport Theory
Author :
Barbaresco, Frédéric
Author_Institution :
Adv. Developments Dept., Thales Air Syst., Limours, France
Abstract :
In the framework of Optimal Transport Theory, Fréchet-Wasserstein distance could be used to define distance for signal radar measures modeled by multivariate Gaussian laws with positive curvature geometry. We compare this approach with Information geometry for Covariance Radar Matrices Processing, where Fisher metric and Siegel-Rao distance provides geometry of negative curvature.
Keywords :
Gaussian processes; geometry; matrix algebra; radar signal processing; transport processes; Fisher metric distance; Frechet distance; Frechet-Wasserstein distance; Siegel-Rao distance; covariance radar matrices processing; geometric radar processing; information geometry; multivariate Gaussian laws; negative curvature; optimal transport theory; positive curvature geometry; signal radar measures; Covariance matrix; Information geometry; Level measurement; Manifolds; Radar; Symmetric matrices;
Conference_Titel :
Radar Symposium (IRS), 2011 Proceedings International
Conference_Location :
Leipzig
Print_ISBN :
978-1-4577-0138-2
