Design Flow for Real-Time Face Mask Detection Using PYNQ System-on-Chip Platform

Abstract

Study shows that mask-wearing is a critical factor in stopping the COVID-19 transmission. By the time of this article, most US states have mandated face masking in public space. Therefore, real-time face mask detection becomes an essential application to prevent the spread of the pandemic. This study will present a face mask detection system that can detect and monitor mask-wearing from camera feeds and alert when there is a violation. The face mask detection algorithm uses Haar cascade classifier (HCC) to find facial features from the camera feed and then utilizes it to detect the mask-wearing status. The detection system runs on a PYNQ-Z2 all-programmable SoC platform, where it will pipeline the camera feed through the FPGA unit and carry out the face mask detection algorithm in the ARM core. Potential delays are analyzed, and efforts are made to reduce them to achieve real-time detection. The experiment result shows that the presented system achieves a real-time 45fps 720p Video output, with a face mask detection response of 0.13s.