Near out-of-distribution detection for low-resolution radar micro-Doppler signatures

TL;DR

This paper explores near out-of-distribution detection for low-resolution radar micro-Doppler signatures, comparing deep and non-deep methods, and investigates training strategies and contamination effects in a critical radar target detection context.

Contribution

It introduces a novel OODD use case for radar targets, compares multiple detection methods, and analyzes training strategies including contamination effects.

Findings

Covariance representation helps discriminate signatures effectively.

Deep and non-deep OODD methods show varying performance.

Training set contamination impacts detection accuracy.

Abstract

Near out-of-distribution detection (OODD) aims at discriminating semantically similar data points without the supervision required for classification. This paper puts forward an OODD use case for radar targets detection extensible to other kinds of sensors and detection scenarios. We emphasize the relevance of OODD and its specific supervision requirements for the detection of a multimodal, diverse targets class among other similar radar targets and clutter in real-life critical systems. We propose a comparison of deep and non-deep OODD methods on simulated low-resolution pulse radar micro-Doppler signatures, considering both a spectral and a covariance matrix input representation. The covariance representation aims at estimating whether dedicated second-order processing is appropriate to discriminate signatures. The potential contributions of labeled anomalies in training, self-supervised learning, contrastive learning insights and innovative training losses are discussed, and the impact of training set contamination caused by mislabelling is investigated.