Robust Multiple-Measurement Sparsity-Aware STAP with Bayesian Variational Autoencoder

Due to the shortage of independent and identically distributed (i.i.d.) training samples, space−time adaptive processing (STAP) often suffers remarkable performance degradation in the heterogeneous clutter environment. Sparse recovery (SR) techniques have been introduced into STAP for the benefit of...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Remote sensing (Basel, Switzerland) Ročník 14; číslo 15; s. 3800
Hlavní autoři: Zhang, Chenxi, Zhao, Huiliang, Chen, Wenchao, Chen, Bo, Wang, Penghui, Jia, Changrui, Liu, Hongwei
Médium: Journal Article
Jazyk:angličtina
Vydáno: Basel MDPI AG 01.08.2022
Témata:
Adaptive sampling
Airborne radar
Algorithms
Bayesian analysis
Bayesian theory
Clutter
clutter plus noise covariance matrix (CCM)
clutter suppression
Computer applications
Dictionaries
Echoes
Machine learning
Mathematical models
Methods
Parameters
Performance degradation
Remote sensing
Robustness
space and time
Space-time adaptive processing
space−time adaptive processing (STAP)
sparse recovery (SR)
Sparsity
Training
variational autoencoder (VAE)
ISSN:2072-4292, 2072-4292
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Due to the shortage of independent and identically distributed (i.i.d.) training samples, space−time adaptive processing (STAP) often suffers remarkable performance degradation in the heterogeneous clutter environment. Sparse recovery (SR) techniques have been introduced into STAP for the benefit of the drastically reduced training requirement, but they are incompletely robust for involving the tricky selection of hyper−parameters or the undesirable point estimation for parameters. Given this issue, we incorporate the Multiple−measurement Complex−valued Variational relevance vector machines (MCV) to model the space−time echoes and provide a Gibbs−sampling−based method to estimate posterior distributions of parameters accurately. However, the Gibbs sampler require quantities of iterations, as unattractive as traditional Bayesian type SR−STAP algorithms when the real−time processing is desired. To address this problem, we further develop the Bayesian Autoencoding MCV for STAP (BAMCV−STAP), which builds the generative model according to MCV and approximates posterior distributions of parameters with an inference network pre−trained off−line, to realize fast reconstruction of measurements. Experimental results on simulated and measured data demonstrate that BAMCV−STAP can achieve suboptimal clutter suppression in terms of the output signal to interference plus noise ratio (SINR) loss, as well as the attractive real−time processing property in terms of the convergence rate and computational loads.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2072-4292
2072-4292
DOI:10.3390/rs14153800