# A MIMO Radar-based Few-Shot Learning Approach for Human-ID

arXiv: https://arxiv.org/abs/2110.08595 · HTML: https://mlsanity.com/paper/2110.08595/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 37 references that are in the map.
- First posted on arXiv 16 Oct 2021.

## Builds on (most cited first, 6 of 6)

- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Generalizing from a Few Examples: A Survey on Few-Shot Learning](https://mlsanity.com/paper/1904.05046/) (2019)
- [Multi-Person Continuous Tracking and Identification from mm-Wave micro-Doppler Signatures](https://mlsanity.com/paper/2003.03571/) (2020)
- [Person Identification and Body Mass Index: A Deep Learning-Based Study on Micro-Dopplers](https://mlsanity.com/paper/1811.07173/) (2018)
- [Doppler Radar for the Extraction of Biomechanical Parameters in Gait Analysis](https://mlsanity.com/paper/2005.05280/) (2020)
- [Stairs Detection for Enhancing Wheelchair Capabilities Based on Radar Sensors](https://mlsanity.com/paper/1711.09206/) (2017)

## Built on by (most cited first, 3 of 3)

- [Pedestrian Recognition with Radar Data-Enhanced Deep Learning Approach Based on Micro-Doppler Signatures](https://mlsanity.com/paper/2306.08303/) (2023)
- [A MIMO Radar-Based Metric Learning Approach for Activity Recognition](https://mlsanity.com/paper/2111.01939/) (2021)
- [XTransfer: Modality-Agnostic Few-Shot Model Transfer for Human Sensing at the Edge](https://mlsanity.com/paper/2506.22726/) (2025)

## Abstract (arXiv)

Radar for deep learning-based human identification has become a research area of increasing interest. It has been shown that micro-Doppler (μ-D) can reflect the walking behavior through capturing the periodic limbs' micro-motions. One of the main aspects is maximizing the number of included classes while considering the real-time and training dataset size constraints. In this paper, a multiple-input-multiple-output (MIMO) radar is used to formulate micro-motion spectrograms of the elevation angular velocity (μ-ω). The effectiveness of concatenating this newly-formulated spectrogram with the commonly used μ-D is investigated. To accommodate for non-constrained real walking motion, an adaptive cycle segmentation framework is utilized and a metric learning network is trained on half gait cycles (≈ 0.5 s). Studies on the effects of various numbers of classes (5--20), different dataset sizes, and varying observation time windows 1--2 s are conducted. A non-constrained walking dataset of 22 subjects is collected with different aspect angles with respect to the radar. The proposed few-shot learning (FSL) approach achieves a classification error of 11.3 % with only 2 min of training data per subject.