A MIMO Radar-Based Metric Learning Approach for Activity Recognition

TL;DR

This paper introduces a novel MIMO radar-based method combining micro-Doppler and micro-rotation signatures for improved human activity recognition, achieving high accuracy with limited training data.

Contribution

It proposes a new micro-motion spectrogram for angular velocity and applies a metric learning approach, including few-shot learning, to enhance activity classification performance.

Findings

Achieved 88.9% accuracy with combined signatures.

Demonstrated effective activity recognition with small datasets.

Implemented few-shot learning for fall detection with 86.42% accuracy.

Abstract

Human activity recognition is seen of great importance in the medical and surveillance fields. Radar has shown great feasibility for this field based on the captured micro-Doppler ({\mu}-D) signatures. In this paper, a MIMO radar is used to formulate a novel micro-motion spectrogram for the angular velocity ({\mu}-{\omega}) in non-tangential scenarios. Combining both the {\mu}-D and the {\mu}-{\omega} signatures have shown better performance. Classification accuracy of 88.9% was achieved based on a metric learning approach. The experimental setup was designed to capture micro-motion signatures on different aspect angles and line of sight (LOS). The utilized training dataset was of smaller size compared to the state-of-the-art techniques, where eight activities were captured. A few-shot learning approach is used to adapt the pre-trained model for fall detection. The final model has shown a classification accuracy of 86.42% for ten activities.