Subject stabilisation based on the precisely detected face position in the visual input and computer systems and computer-implemented methods for implementing thereof

Abstract

In some embodiments, the present invention provides for an exemplary computer system that may include: a camera component configured to acquire a visual content, wherein the visual content having a plurality of frames with a visual representation of a face of a person; a processor configured to: apply, for each frame, a multi-dimensional face detection regressor for fitting at least one meta-parameter to detect or to track a plurality of multi-dimensional landmarks representative of a face; apply a face movement detection algorithm to identify each displacement of each respective multi-dimensional landmark between frames; and apply a face movement compensation algorithm to generate a face movement compensated output that stabilizes the visual representation of the face.

What is claimed is: 
     
         1 . A method, comprising:
 obtaining, by at least one processor, a plurality of sequential visual representations having a face of at least one subject;   applying, by the at least one processor, a face detection algorithm to detect an initial presence of the face of the at least one subject within an initial visual representation of the plurality of sequential visual representations;   wherein the initial visual representation is a first visual representation in which the initial presence of the face of the at least one subject has been detected for a first time in the plurality of sequential visual representations;   constructing, by the at least one processor, a face model of the face of the at least one subject based, at least in part, on the n initial presence; and   tracking, by the at least one processor, the face of the at least one subject in at least one subsequent visual representation of the plurality of sequential visual representations, based on applying a predetermined filter to a plurality of subsequent face models where each subsequent face model is a prediction of how the face of the at least one subject would appear in the at least one subsequent visual representation.   
     
     
         2 . A system comprising:
 a portable electronic device having a camera, wherein the camera is configured to acquire a plurality of sequential visual representations having a face of at least one subject;   a non-transient computer memory storing software instructions; and   at least one processor configured, when executing one or more of the software instructions, to perform at least the following:   
       obtaining, by at least one processor, a plurality of sequential visual representations having a face of at least one subject;
 applying a face detection algorithm to detect an initial presence of the face of the at least one subject within an initial visual representation of the plurality of sequential visual representations; 
 wherein the initial visual representation is a first visual representation in which the initial presence of the face of the at least one subject has been detected for a first time in the plurality of sequential visual representations; 
 constructing a face model of the face of the at least one subject based, at least in part, on the n initial presence; and 
 tracking the face of the at least one subject in at least one subsequent visual representation of the plurality of sequential visual representations, based on applying a predetermined filter to a plurality of subsequent face models where each subsequent face model is a prediction of how the face of the at least one subject would appear in the at least one subsequent visual representation.