HIGHLIGHTING A PERSON'S FACE IN A VIDEO STREAM TO MONITOR EMPLOYEES' COMPLIANCE WITH THE SECURITY STATUS DURING WORK AND TRAINING
DOI:
https://doi.org/10.18372/2410-7840.24.16934Keywords:
security, facial selection, object recognition, monitoring, neural networks, MobileSSDAbstract
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.
Downloads
Published
Issue
Section
License
Authors who publish with this journal agree to the following terms:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
