Effectiveness of Detection-based and Regression-based Approaches for Estimating Mask-Wearing Ratio

TL;DR

This paper compares detection-based and regression-based methods for estimating mask-wearing ratios in images, introducing a new large-scale dataset and demonstrating the strengths of each approach in accuracy and efficiency.

Contribution

It presents two novel methods for mask ratio estimation and introduces the first large-scale dataset for this task, advancing research in image-based health monitoring.

Findings

RetinaFace-based method achieves higher accuracy in various scenarios.

CSRNet-based method offers faster processing due to its compactness.

The new NFM dataset contains over 580,000 face annotations from street-view videos.

Abstract

Estimating the mask-wearing ratio in public places is important as it enables health authorities to promptly analyze and implement policies. Methods for estimating the mask-wearing ratio on the basis of image analysis have been reported. However, there is still a lack of comprehensive research on both methodologies and datasets. Most recent reports straightforwardly propose estimating the ratio by applying conventional object detection and classification methods. It is feasible to use regression-based approaches to estimate the number of people wearing masks, especially for congested scenes with tiny and occluded faces, but this has not been well studied. A large-scale and well-annotated dataset is still in demand. In this paper, we present two methods for ratio estimation that leverage either a detection-based or regression-based approach. For the detection-based approach, we improved the state-of-the-art face detector, RetinaFace, used to estimate the ratio. For the regression-based approach, we fine-tuned the baseline network, CSRNet, used to estimate the density maps for masked and unmasked faces. We also present the first large-scale dataset, the ``NFM dataset,'' which contains 581,108 face annotations extracted from 18,088 video frames in 17 street-view videos. Experiments demonstrated that the RetinaFace-based method has higher accuracy under various situations and that the CSRNet-based method has a shorter operation time thanks to its compactness.