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

arXiv: https://arxiv.org/abs/2204.10541 · HTML: https://mlsanity.com/paper/2204.10541/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 45 references that are in the map.
- First posted on arXiv 22 Apr 2022.

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

- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [A Vision-based Social Distancing and Critical Density Detection System for COVID-19](https://mlsanity.com/paper/2007.03578/) (2020)
- [Robust and Energy-efficient PPG-based Heart-Rate Monitoring](https://mlsanity.com/paper/2203.16339/) (2022)
- [Pruning In Time (PIT): A Lightweight Network Architecture Optimizer for Temporal Convolutional Networks](https://mlsanity.com/paper/2203.14768/) (2022)
- [Home Activity Monitoring using Low Resolution Infrared Sensor](https://mlsanity.com/paper/1811.05416/) (2018)

## Built on by (most cited first, 1 of 1)

- [Efficient Deep Learning Models for Privacy-preserving People Counting on Low-resolution Infrared Arrays](https://mlsanity.com/paper/2304.06059/) (2023)

## Abstract (arXiv)

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 9.38-68.57μJ.