HIGHLIGHTING A PERSON'S FACE IN A VIDEO STREAM TO MONITOR EMPLOYEES' COMPLIANCE WITH THE SECURITY STATUS DURING WORK AND TRAINING

Authors

DOI:

https://doi.org/10.18372/2410-7840.24.16934

Keywords:

security, facial selection, object recognition, monitoring, neural networks, MobileSSD

Abstract

The study is devoted to the problem of highlighting a person's face in a video stream, the areas of application of the facial discharge function are considered. The requirements for the mechanisms for solving this problem are analyzed in case of using them for monitoring, online, human presence in the workplace, in front of a computer. The principles by which the selection of objects (a person's face) in the video stream is indicated.  As a mechanism for solving this problem, it is proposed to use MobileSSD technology, which is a combination of MobileNetV2 and SSD convolutional neural networks. The principle of actions of selected neural networks and the reasons for their election are analyzed.  To study the feasibility of using the proposed technology to solve the problem, software was developed on the basis of the proposed technology and a number of experiments were conducted with its help. Based on the results of the experiments, conclusions were drawn regarding the feasibility of using the proposed technology to solve the problem, the advantages and disadvantages are formulated, the conditions for the effective use of this technology and these recommendations for further improvement of the proposed mechanism for solving the problem of allocating a person's face in a video stream for monitoring, online, the presence of a person in front of a computer are indicated.

Published

2022-11-23