Spatiotemporal Radar Gesture Recognition with Hybrid Spiking Neural Networks: Balancing Accuracy and Efficiency

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mazzieri, Riccardo, Cicciarella, Eleonora, Pegoraro, Jacopo, Corradi, Federico, Rossi, Michele
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911181572145152
author Mazzieri, Riccardo
Cicciarella, Eleonora
Pegoraro, Jacopo
Corradi, Federico
Rossi, Michele
author_facet Mazzieri, Riccardo
Cicciarella, Eleonora
Pegoraro, Jacopo
Corradi, Federico
Rossi, Michele
contents Radar-based Human Activity Recognition (HAR) offers privacy and robustness over camera-based methods, yet remains computationally demanding for edge deployment. We present the first use of Spiking Neural Networks (SNNs) for radar-based HAR on aircraft marshalling signal classification. Our novel hybrid architecture combines convolutional modules for spatial feature extraction with Leaky Integrate-and-Fire (LIF) neurons for temporal processing, inherently capturing gesture dynamics. The model reduces trainable parameters by 88\% with under 1\% accuracy loss compared to baselines, and generalizes well to the Soli gesture dataset. Through systematic comparisons with Artificial Neural Networks, we demonstrate the trade-offs of spiking computation in terms of accuracy, latency, memory, and energy, establishing SNNs as an efficient and competitive solution for radar-based HAR.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23303
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Spatiotemporal Radar Gesture Recognition with Hybrid Spiking Neural Networks: Balancing Accuracy and Efficiency
Mazzieri, Riccardo
Cicciarella, Eleonora
Pegoraro, Jacopo
Corradi, Federico
Rossi, Michele
Neural and Evolutionary Computing
Radar-based Human Activity Recognition (HAR) offers privacy and robustness over camera-based methods, yet remains computationally demanding for edge deployment. We present the first use of Spiking Neural Networks (SNNs) for radar-based HAR on aircraft marshalling signal classification. Our novel hybrid architecture combines convolutional modules for spatial feature extraction with Leaky Integrate-and-Fire (LIF) neurons for temporal processing, inherently capturing gesture dynamics. The model reduces trainable parameters by 88\% with under 1\% accuracy loss compared to baselines, and generalizes well to the Soli gesture dataset. Through systematic comparisons with Artificial Neural Networks, we demonstrate the trade-offs of spiking computation in terms of accuracy, latency, memory, and energy, establishing SNNs as an efficient and competitive solution for radar-based HAR.
title Spatiotemporal Radar Gesture Recognition with Hybrid Spiking Neural Networks: Balancing Accuracy and Efficiency
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2509.23303