Privacy-preserving Social Distance Monitoring on Microcontrollers with Low-Resolution Infrared Sensors and CNNs
This provides a privacy-preserving, low-cost solution for indoor social distance monitoring, though it is incremental as it applies existing CNN methods to a new sensor type and dataset.
The paper tackled social distance monitoring using low-resolution infrared sensors and CNNs, achieving 86.3% balanced accuracy on a new dataset, which outperforms a state-of-the-art deterministic algorithm by 25.3 percentage points, with models deployed on microcontrollers showing latencies of 0.73-5.33ms and energy consumption of 9.38-68.57μJ per inference.
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.