Design and Implementation of Safety Helmet Detection System Based on YOLOv5

Abstract

In order to reduce safety accidents caused by non-standard wearing of helmets, deep learning target detection technology is applied to construction safety detection scenarios, and a helmet detection algorithm based on YOLO v5 is proposed, which can realize real-time detection of helmet wearing. The deep learning part uses the K-means algorithm to cluster the dimensions of the target frame, and Yolov5s.pt is used for deep learning training. During training, the size of the input image is changed to increase the adaptability of the model, and the hyperparameters and optimizer are adjusted to be the best after improvement. The detection model has an accuracy rate of 90%, and the detection speed has reached 37.8fps, which meets the requirements of real-time detection of helmets. Through the combination of this model and hardware such as cameras, a real-time detection of whether a person wears a helmet is designed and implemented. The system realizes the three functions of picture detection, video detection and real-time monitoring.