Neural Network-Based Multi-Target Detection within Correlated Heavy-Tailed Clutter

TL;DR

This paper introduces a deep learning-based method for multi-target detection in radar systems affected by correlated heavy-tailed clutter, outperforming traditional detectors across various scenarios.

Contribution

It proposes a unified neural network model that effectively detects multiple targets in complex clutter conditions, simplifying architecture and training.

Findings

Outperforms CA-CFAR, OS-CFAR, and ANMF detectors in detection probability

Effective across various SCNRs and clutter distributions

Validated with real radar echoes and simulations

Abstract

This work addresses the problem of range-Doppler multiple target detection in a radar system in the presence of slow-time correlated and heavy-tailed distributed clutter. Conventional target detection algorithms assume Gaussian-distributed clutter, but their performance is significantly degraded in the presence of correlated heavy-tailed distributed clutter. Derivation of optimal detection algorithms with heavy-tailed distributed clutter is analytically intractable. Furthermore, the clutter distribution is frequently unknown. This work proposes a deep learning-based approach for multiple target detection in the range-Doppler domain. The proposed approach is based on a unified NN model to process the time-domain radar signal for a variety of signal-to-clutter-plus-noise ratios (SCNRs) and clutter distributions, simplifying the detector architecture and the neural network training procedure. The performance of the proposed approach is evaluated in various experiments using recorded radar echoes, and via simulations, it is shown that the proposed method outperforms the conventional cell-averaging constant false-alarm rate (CA-CFAR), the ordered-statistic CFAR (OS-CFAR), and the adaptive normalized matched-filter (ANMF) detectors in terms of probability of detection in the majority of tested SCNRs and clutter scenarios.