Abstract At construction sites, wearing hard hats is an important and effective measure to protect workers from accidental injury. In order to remind workers to wear hard hats at all times, it is necessary to automate the detection process of hard hat-wearing. Limited to the environment, human posture, personal privacy and other elements, traditional detection methods often cannot detect the wearing of hard hats in a handy and quick manner. In the paper, an improved deep learning model based on yolov4 is proposed to detect hard hat-wearing. The accuracy and speed of the model are optimized by replacing the cumbersome overlapping of multiple convolution modules in the feature pyramid of yolov4 with cross-stage hierarchy modules. At the same time, since hard hat detection is to detect small targets, we improve the performance of yolov4 to detect small targets by changing the yolov4 feature layer output and linear transformation of anchors. The final algorithm obtains a mean average precision of 93.37 in hard hat detection, with an increase of 3.15 compared with that of the original yolov4.
展开▼