Construction site safety helmet identification method and system

Abstract

The invention provides a construction site safety helmet identification method and system. The method comprises the steps of: obtaining image information collected in real time, and carrying out scene enhancement on the image information; enabling a trunk feature extraction network to extract features of the image information for training a learning model; using a channel pruning technology to the learning model; performing multi-scale feature fusion on feature fusion neck networks of different scales, and optimizing the learning model; and performing prediction according to an output result of the learning model. According to the method of the invention, scene enhancement is carried out on image information in a data set, the trunk feature extraction network carries out feature extraction on the image information, the learning model is trained, channel pruning is carried out on the learning model, and features of different scales are fused, so that the learning model is optimized; and whether a safety helmet is worn in an image is predicted according to the learning model, so that rapid identification of the safety helmet is realized.

Description

technical field [0001] The invention relates to the field of deep learning technology, in particular to a construction site safety helmet identification method and system. Background technique [0002] As a personal head protection product, the safety helmet can effectively prevent and reduce the injury to the human head when the operator encounters falling objects or self-falling during production operations. It is a necessary safety measure for construction workers on road construction sites to wear safety helmets, which can protect the personal safety of construction workers to a certain extent. It is of great significance to detect and count people wearing helmets of various colors at road construction sites. Through the statistics of construction personnel wearing safety helmets of different colors entering and leaving the construction site, it is convenient to realize the reasonable allocation of resources and effectively manage personnel; it can also issue timely ala...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the deficiencies in the prior art, the present invention provides a construction site helmet identification method and system to solve the technical problem that the helmet identification effect in the related art is not ideal

Images