English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We address the estimation of the scatter matrix of a scale mixture ofGaussian stationary autoregressive vectors. This is equivalent to consider theestimation of a structured scatter matrix of a Spherically Invariant RandomVector (SIRV) whose structure comes from an autoregressive modelization. TheToeplitz structure representative of stationary models is a particular case forthe class of structures we consider. For Gaussian autoregressive processes,Burg method is often used in case of stationarity for its efficiency when fewsamples are available. Unfortunately, if we directly apply these methods toestimate the common scatter matrix of N vectors coming from a non-Gaussiandistribution, their efficiency will strongly decrease. We propose then to adaptthese methods to scale mixtures of autoregressive vectors by changing theenergy functional minimized in the Burg algorithm. Moreover, we study severalapproaches of robust modification of the introduced Burg algorithms, based onFr\'echet medians defined for the Euclidean or the Poincar\'e metric, inpresence of outliers or contaminating distributions. The considered structuredmodelization is motivated by radar applications, the performances of ourmethods will then be compared to the very popular Fixed Point estimator andOS-CFAR detector through radar simulated scenarios.

Robust Burg Estimation of Radar Scatter Matrix for Autoregressive structured SIRV based on Fr\'echet medians