Radar Detection through Rectified Flow Matching

TL;DR

This paper introduces D-RFM, a novel radar detection method using rectified flow matching that effectively handles non-Gaussian clutter and noise, improving accuracy and robustness over existing techniques.

Contribution

It presents a new detection approach based on learning a velocity field to map radar observations to a Gaussian space, enabling better detection in complex clutter environments.

Findings

Effective detection under Gaussian and non-Gaussian clutter

High robustness to noise and clutter variations

Improved computational efficiency

Abstract

Radar target detection in the presence of a mixture of non-Gaussian clutter and white thermal noise is a challenging problem. This paper proposes a Rectified Flow Matching-based method for radar detection, termed D-RFM. Unlike existing detectors, D-RFM learns a mapping from a standard Gaussian distribution to radar observations by capturing the underlying velocity field. Detection is then performed by inverse mapping test samples into the latent Gaussian space using the learned velocity field, with targets identified as deviations from the learned distribution. Experimental results demonstrate the efficacy of the proposed method under both Gaussian and non-Gaussian clutter plus additive white Gaussian noise, highlighting its accuracy, robustness, and computational efficiency.