Privacy-preserving Social Distance Monitoring on Microcontrollers with Low-Resolution Infrared Sensors and CNNs

TL;DR

This paper demonstrates that low-resolution IR sensors combined with small CNNs can accurately monitor social distancing in indoor spaces while preserving privacy, and can be efficiently run on microcontrollers.

Contribution

It introduces a CNN-based method for social distance monitoring using IR sensors that can be deployed directly on microcontrollers, ensuring privacy and low power consumption.

Findings

Achieves 86.3% accuracy on a new dataset.

Outperforms a state-of-the-art deterministic algorithm.

Models run with low latency and energy on microcontrollers.

Abstract

Low-resolution infrared (IR) array sensors offer a low-cost, low-power, and privacy-preserving alternative to optical cameras and smartphones/wearables for social distance monitoring in indoor spaces, permitting the recognition of basic shapes, without revealing the personal details of individuals. In this work, we demonstrate that an accurate detection of social distance violations can be achieved processing the raw output of a 8x8 IR array sensor with a small-sized Convolutional Neural Network (CNN). Furthermore, the CNN can be executed directly on a Microcontroller (MCU)-based sensor node. With results on a newly collected open dataset, we show that our best CNN achieves 86.3% balanced accuracy, significantly outperforming the 61% achieved by a state-of-the-art deterministic algorithm. Changing the architectural parameters of the CNN, we obtain a rich Pareto set of models, spanning 70.5-86.3% accuracy and 0.18-75k parameters. Deployed on a STM32L476RG MCU, these models have a latency of 0.73-5.33ms, with an energy consumption per inference of 9.38-68.57{\mu}J.