Dressing identification method, device and equipment and computer readable medium

Abstract

The invention relates to a dressing identification method, device and equipment and a computer readable medium. The method comprises the steps that a target image is acquired, wherein the target image is acquired from a production operation site of an operator, and the operator needs to wear according to requirements of the production operation site; the target image is input into a first identification model, an identification result output by the first identification model is obtained, wherein the identification result is obtained by clustering dressing features of the clothing area of the operator in the target image; and a dressing judgment result of the operator is determined according to the identification result. According to the method, the dressing features of the operator are extracted more accurately by using the clustering algorithm, the dressing features are identified based on the deep learning technology, whether the operator work safely or not can be identified more accurately, the technical problem of low operator dressing identification accuracy is solved, and due to the fact that the neural network model is high in stability and robustness, the technical scheme is wider in application range.

Description

technical field [0001] The present application relates to the technical field of deep learning, and in particular to a clothing recognition method, device, equipment and computer-readable medium. Background technique [0002] When workers perform production operations in production sites such as tunnels, mines, and building construction sites, it is very important to standardize wearing safety helmets and safety clothing. In order to ensure the personal safety of workers, it is necessary to supervise and warn whether workers wear safety helmets and safety clothing. [0003] At present, in related technologies, pedestrian detection is performed by using the HOG (Histogram of Oriented Gradient, histogram of oriented gradient) algorithm to obtain the region of interest of the human body, and the original RGB model image is converted into an HSV model image, and then the HSV model image is converted according to the color threshold. The image is converted into a binary image; t...

AI Technical Summary

Problems solved by technology

[0005] This application provides a clothing recognition method, device, equipment and computer-readable medium to solve the technical problem of low accuracy in personnel clothing recognition

Images