DopplerGLRTNet for Radar Off-Grid Detection

TL;DR

DopplerGLRTNet is a lightweight neural network that improves off-grid radar target detection by approximating continuous Doppler estimation, reducing computational cost, and enhancing robustness compared to traditional methods.

Contribution

It introduces DopplerGLRTNet, a novel amortized off-grid GLRT approach that predicts continuous Doppler and enhances detection performance with lower computational cost.

Findings

Mitigates off-grid saturation effects.

Approaches dense-scan performance at reduced cost.

Improves robustness to covariance mismatch.

Abstract

Off-grid targets whose Doppler (or angle) does not lie on the discrete processing grid can severely degrade classical normalized matched-filter (NMF) detectors: even at high SNR, the detection probability may saturate at operationally relevant low false-alarm rates. A principled remedy is the continuous-parameter GLRT, which maximizes a normalized correlation over the parameter domain; however, dense scanning increases test-time cost and remains sensitive to covariance mismatch through whitening. We propose DopplerGLRTNet, an amortized off-grid GLRT: a lightweight regressor predicts the continuous Doppler within a resolution cell from the whitened observation, and the detector outputs a single GLRT/NMF-like score given by the normalized matched-filter energy at the predicted Doppler. Monte Carlo simulations in Gaussian and compound-Gaussian clutter show that DopplerGLRTNet mitigates off-grid saturation, approaches dense-scan performance at a fraction of its cost, and improves robustness to covariance estimation at the same empirically calibrated Pfa.