Improve Accuracy and Response Time in Real-time Facemask Detection System

Abstract

To improve people’s health safety in public places and strengthen the government’s epidemic prevention and control measures, the accuracy and response speed of mask detection in public areas need to be improved. The current real-time mask detection algorithm is developed based on a one-stage object detection algorithm in deep learning. The key to the algorithm research is how to improve the accuracy and response speed of the algorithm at the same time to meet the efficiency of real-time monitoring. Few of the current algorithms can achieve an accuracy of more than 90% under the same data set, and the FPS can also achieve the standard of real-time monitoring.