FIELD: artificial intelligence.
SUBSTANCE: invention relates to the field of artificial intelligence, in particular, to digital methods for automatic monitoring of the level of people's safety, as well as to human-machine interaction. It can be used in situations where it is necessary to effectively prevent outbreaks of various epidemics and their further spread, or in cases where there is a need to automatically check the availability of personal protective equipment on the faces of medical workers and people of other professions who must move around the territories of various institutions and contact with other people only in personal protective equipment. This invention is capable of both intellectual analysis of the voice characteristics of people from their speech to determine the presence of personal protective equipment in the process of speaking, and intellectual analysis of facial characteristics of people from video data to localize and detect the presence of personal protective equipment in the process of performing any actions at a certain moment of time. Support for simultaneous signal processing of both modalities makes it possible to achieve more accurate audio-visual predictions for the final actions, depending on a certain degree of individual protection on a person's face. An audio capture device is a device capable of receiving audio data. The video capture device is a device capable of receiving colour optical video data. The technical problem to be solved by the present invention is the need to expand the functionality of various methods by using intelligent analysis of audio-visual information to more accurately recognize various personal protective equipment on people's faces through the combination of information from audio and video modalities.
EFFECT: expanded functionality of digital methods for automatic monitoring of the level of people's safety.
1 cl, 1 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| METHOD OF MULTIMODAL CONTACTLESS CONTROL OF MOBILE INFORMATION ROBOT | 2020 |
|
RU2737231C1 |
| METHOD FOR GENERATING COLOR PROTECTIVE MASK ON IMAGES OF PEOPLE'S FACES | 2022 |
|
RU2790018C1 |
| SIMULTANEOUS RECOGNITION OF PERSON ATTRIBUTES AND IDENTIFICATION OF PERSON IN ORGANIZING PHOTO ALBUMS | 2018 |
|
RU2710942C1 |
| METHOD FOR IDENTIFYING CHANGED HUMAN FACE | 2023 |
|
RU2804261C1 |
| RAPID TWO-LAYER NEURAL NETWORK SYNTHESIS OF REALISTIC IMAGES OF A NEURAL AVATAR BASED ON A SINGLE IMAGE | 2020 |
|
RU2764144C1 |
| ALGORITHM OF INTEGRATED REMOTE CONTACTLESS MULTICHANNEL ANALYSIS OF PSYCHOEMOTIONAL AND PHYSIOLOGICAL STATE OF OBJECT BASED ON AUDIO AND VIDEO CONTENT | 2017 |
|
RU2708807C2 |
| SYSTEM AND METHOD OF RECORDING TWO-DIMENSIONAL IMAGES | 2005 |
|
RU2365995C2 |
| METHOD FOR DETERMINING FACE AUTHORITY BY SEGMENTATION MASKS | 2021 |
|
RU2758966C1 |
| METHOD FOR 3D RECONSTRUCTION OF A HUMAN HEAD TO OBTAIN A RENDER IMAGE OF A PERSON | 2022 |
|
RU2786362C1 |
| METHOD OF CONTROLLING TELEVISION USING MULTIMODAL INTERFACE | 2010 |
|
RU2422878C1 |
