The environment of production site in industrial enterprises is complex and dangerous, so operating personnel is required to wear labour protection appliance to ensure to be protected against personal injury in the operation process. In this paper, a detection system for personnel to wear labour protection appliance based on deep learning is designed to detect such objects as the personnel, safety helmet and CO alarm apparatus in the image as well as normalize the inference algorithm of wearing based on the deep learning object detection model so that the automatic identification of wearing labor protection appliance for operating personnel is realized and the accuracy rate is over 90%.

machine vision  /  convolutional neural network  /  intelligent identification