Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Radar Detection through Rectified Flow Matching

P. Meena, Y. A. Rouzoumka, J. Pinsolle, C. Ren, M. N. El Korso, J. -P. Ovarlez

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.

Radar Detection through Rectified Flow Matching

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.
Paper Structure (11 sections, 9 equations, 3 figures, 1 table)

This paper contains 11 sections, 9 equations, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Statistical Model
  3. Rectified Flow-based Radar Detection
  4. Training
  5. Detection
  6. Results and Discussion
  7. Experimental Setup:
  8. SNR vs Pd analysis for zero Doppler bin
  9. SNR vs Pd analysis for all Doppler bins
  10. Computational complexity analysis
  11. Conclusion

Figures (3)

  • Figure 1: Overall framework for proposed rectified flow matching-based radar target detection.
  • Figure 2: Performance comparison in terms of $p_d$, under different noise for Doppler bin $d = 0$ ($P_{fa}$ = $10^{-2}$).
  • Figure 3: Comparison of $P_d$-SNR-Doppler bin map obtained using AMF-SCM, SVDD, ANMF-FP, and D-RFM for different cases. (Top row): cGN + AWGN (Bottom row): cCGN + AWGN.