# Gesture Recognition for FMCW Radar on the Edge

arXiv: https://arxiv.org/abs/2310.08876 · HTML: https://mlsanity.com/paper/2310.08876/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 11 references that are in the map.
- First posted on arXiv 13 Oct 2023.

## Builds on (most cited first, 1 of 1)

- [Data Augmentation for Robust Keyword Spotting under Playback Interference](https://mlsanity.com/paper/1808.00563/) (2018)

## Built on by (most cited first, 5 of 5)

- [Interpretable Rule-Based System for Radar-Based Gesture Sensing: Enhancing Transparency and Personalization in AI](https://mlsanity.com/paper/2410.12806/) (2024)
- [Complying with the EU AI Act: Innovations in Explainable and User-Centric Hand Gesture Recognition](https://mlsanity.com/paper/2503.15528/) (2025)
- [Learning Interpretable Rules from Neural Networks: Neurosymbolic AI for Radar Hand Gesture Recognition](https://mlsanity.com/paper/2506.22443/) (2025)
- [Resonate-and-Fire Spiking Neurons for Target Detection and Hand Gesture Recognition: A Hybrid Approach](https://mlsanity.com/paper/2405.19351/) (2024)
- [GenFacts-Generative Counterfactual Explanations for Multi-Variate Time Series](https://mlsanity.com/paper/2509.20936/) (2025)

## Abstract (arXiv)

This paper introduces a lightweight gesture recognition system based on 60 GHz frequency modulated continuous wave (FMCW) radar. We show that gestures can be characterized efficiently by a set of five features, and propose a slim radar processing algorithm to extract these features. In contrast to previous approaches, we avoid heavy 2D processing, i.e. range-Doppler imaging, and perform instead an early target detection - this allows us to port the system to fully embedded platforms with tight constraints on memory, compute and power consumption. A recurrent neural network (RNN) based architecture exploits these features to jointly detect and classify five different gestures. The proposed system recognizes gestures with an F1 score of 98.4% on our hold-out test dataset, it runs on an Arm Cortex-M4 microcontroller requiring less than 280 kB of flash memory, 120 kB of RAM, and consuming 75 mW of power.