A MIMO Radar-Based Metric Learning Approach for Activity Recognition

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
$(\mu-\mathrm{D})$
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
$\mu-\mathrm{D}$
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.