Simultaneous Detection of Helmet and Mask Wearing Based on YOLO Improved Algorithm

Abstract

In order to solve the problem of automatic detection of whether workers wear helmets and masks in construction sites, workshops and other scenarios, an improved YOLOv5 algorithm is proposed to improve the accuracy of simultaneous detection of helmets and masks. First, the CIOU_Loss with better effect is adopted, which considers the information of the center point distance of the bounding box and the scale information of the aspect ratio of the bounding box; The probability value of the category is sorted according to the category classification probability obtained by the classifier, which makes the results obtained by NMS more reasonable and effective. The experimental results show that the average accuracy of the improved algorithm for detecting helmet and mask wearing at the same time is 12.7% higher than that of the original algorithm.