Energy-efficient and Privacy-aware Social Distance Monitoring with Low-resolution Infrared Sensors and Adaptive Inference

TL;DR

This paper presents an energy-efficient, privacy-preserving social distance monitoring system using low-resolution IR sensors and adaptive inference on IoT devices, reducing energy use significantly with minimal accuracy loss.

Contribution

It introduces an adaptive inference framework combining a wake-up trigger and quantized CNN, optimized for low-power IoT edge deployment in indoor social distancing applications.

Findings

Energy consumption reduced by 37-57%

Accuracy drop less than 2%

Effective on low-resolution IR sensors

Abstract

Low-resolution infrared (IR) Sensors combined with machine learning (ML) can be leveraged to implement privacy-preserving social distance monitoring solutions in indoor spaces. However, the need of executing these applications on Internet of Things (IoT) edge nodes makes energy consumption critical. In this work, we propose an energy-efficient adaptive inference solution consisting of the cascade of a simple wake-up trigger and a 8-bit quantized Convolutional Neural Network (CNN), which is only invoked for difficult-to-classify frames. Deploying such adaptive system on a IoT Microcontroller, we show that, when processing the output of a 8x8 low-resolution IR sensor, we are able to reduce the energy consumption by 37-57% with respect to a static CNN-based approach, with an accuracy drop of less than 2% (83% balanced accuracy).