Skip to content
Conference Open access

A Clutter Suppression Algorithm via U-Net-structured Attention Deep Network for Airborne Radar

Oct 2026 · European Radar Conference · pp. 57-60 · 0 citations · 13 references

Abstract

Space-Time Adaptive Processing (STAP) demonstrates excellent clutter suppression performance in airborne radar systems when sufficient independent and identically distributed (i.i.d.) samples are available. However, heterogeneous and non-stationary clutter environments often lead to a shortage of i.i.d. samples, degrading conventional STAP methods’ performance. Under small sample conditions, existing sparse recovery-based STAP algorithms achieve effective suppression but suffer from high computational complexity, hindering their application. In this paper, a novel STAP method based on a U-Net-structured deep network incorporating attention mechanisms is proposed to address these challenges, which performs hierarchical feature extraction and reconstruction of the clutter spatial-Doppler spectrum. Once trained, the proposed network can achieve high-resolution reconstruction from the low-resolution clutter spectrum estimated with limited snapshots, thereby enabling efficient clutter suppression. Extensive simulations demonstrate that the proposed STAP algorithm outperforms current mainstream methods in clutter suppression and target detection, proving more suitable for practical applications.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.