English

A MIMO Radar-Based Metric Learning Approach for Activity Recognition

Signal Processing 2021-11-04 v1 Machine Learning

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.

Keywords

Cite

@article{arxiv.2111.01939,
  title  = {A MIMO Radar-Based Metric Learning Approach for Activity Recognition},
  author = {Fady Aziz and Omar Metwally and Pascal Weller and Urs Schneider and Marco F. Huber},
  journal= {arXiv preprint arXiv:2111.01939},
  year   = {2021}
}

Comments

6 pages, 7 figures, 2 tables

R2 v1 2026-06-24T07:23:35.971Z