Saved in:
Bibliographic Details
Main Authors: Bartoli, Pietro, Veronesi, Christian, Bondini, Tommaso, Giudici, Andrea, Zappa, Franco
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.13462
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917491235618816
author Bartoli, Pietro
Veronesi, Christian
Bondini, Tommaso
Giudici, Andrea
Zappa, Franco
author_facet Bartoli, Pietro
Veronesi, Christian
Bondini, Tommaso
Giudici, Andrea
Zappa, Franco
contents Gesture recognition is a cornerstone of Human-Computer Interaction (HCI) for smart eyewear, enabling natural and device-free control in augmented reality environments. Traditional vision-based approaches face significant challenges regarding power consumption, computational latency, and user privacy. This paper proposes a lightweight, privacy-preserving gesture recognition system based on the fusion of low-resolution Time-of-Flight (ToF) and Infrared (IR) thermal sensors. We used an 8 times 8 multizone ToF sensor (VL53L8CH) and an 8 times 8 IR array (AMG8833) to capture complementary depth and thermal cues. A compact Convolutional Neural Network (CNN) with a specialized grouped-convolution architecture is designed to fuse these modalities efficiently on a microcontroller (MCU). Experimental results on a custom dataset of 7 static gestures, validated via k-fold cross-validation, demonstrate that the proposed fusion strategy significantly outperforms single-sensor baselines with an accuracy of 92.3% and a macro F1-score of 0.93. Finally, on-device benchmarks on STM32F4 and STM32H7 MCUs confirm the system's suitability for resource-constrained wearables, requiring only 6,343 parameters and achieving millisecond-level inference latency with a total system power of 50 mW.
format Preprint
id arxiv_https___arxiv_org_abs_2605_13462
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Efficient Sensor Fusion for Gesture Recognition on Resource-Constrained Devices
Bartoli, Pietro
Veronesi, Christian
Bondini, Tommaso
Giudici, Andrea
Zappa, Franco
Machine Learning
Gesture recognition is a cornerstone of Human-Computer Interaction (HCI) for smart eyewear, enabling natural and device-free control in augmented reality environments. Traditional vision-based approaches face significant challenges regarding power consumption, computational latency, and user privacy. This paper proposes a lightweight, privacy-preserving gesture recognition system based on the fusion of low-resolution Time-of-Flight (ToF) and Infrared (IR) thermal sensors. We used an 8 times 8 multizone ToF sensor (VL53L8CH) and an 8 times 8 IR array (AMG8833) to capture complementary depth and thermal cues. A compact Convolutional Neural Network (CNN) with a specialized grouped-convolution architecture is designed to fuse these modalities efficiently on a microcontroller (MCU). Experimental results on a custom dataset of 7 static gestures, validated via k-fold cross-validation, demonstrate that the proposed fusion strategy significantly outperforms single-sensor baselines with an accuracy of 92.3% and a macro F1-score of 0.93. Finally, on-device benchmarks on STM32F4 and STM32H7 MCUs confirm the system's suitability for resource-constrained wearables, requiring only 6,343 parameters and achieving millisecond-level inference latency with a total system power of 50 mW.
title Efficient Sensor Fusion for Gesture Recognition on Resource-Constrained Devices
topic Machine Learning
url https://arxiv.org/abs/2605.13462