Systems and methods for foreground and background processing of content in a live video

A system, comprising:

• a webcam;
• a memory storing instructions;
• a processor coupled to the memory and configured by the instructions to at least:
• generate a user interface, the user interface including a viewing window, the user interface further comprising a toolbar including a selection tool;
• display a live video depicting at least one individual in the viewing window of the user interface;
• generate at least one segmentation mask for the at least one individual depicted in the live video, wherein each of the at least one segmentation mask comprises a body region of each individual and facial feature vectors of a facial region of each individual, wherein each facial feature vector is generated from facial features of each individual, wherein the facial feature vectors are derived by a facial recognition technique, and wherein a separate segmentation mask is generated for each individual, each separate segmentation mask comprising a body region and facial feature vectors of a facial region of a corresponding individual;
• obtain selection of at least one individual depicted in the live video based on operation of the selection tool to designate at least one selected facial feature vector corresponding to the selected at least one individual;
• compare facial feature vectors in a facial region of each of individuals depicted in the live video with the selected at least one facial feature vector corresponding to the selected at least one individual;
• convert the segmentation masks of individuals with a corresponding body region to a filter mask when the facial feature vectors do not match the selected facial feature vector;
• composite the filter mask comprising facial feature vectors that do not match the selected facial feature vector with a background content of the live video to generate composited background content filtering entire individuals corresponding to the facial features vectors that do not match the selected facial feature vector, wherein filtering entire individuals comprises causing both a body region and a facial region of each individual to be hidden from view in the viewing window;
• apply a graphical effect to the composited background content;
• and
• display a modified video comprising the segmentation mask and the composited background content when the selected at least one individual is in a field of view of the webcam.

A non-transitory computer-readable storage medium storing instructions to be implemented by a computing device having a processor, wherein the instructions, when executed by the processor, cause the computing device to at least:

• generate a user interface, the user interface including a viewing window, the user interface further comprising a toolbar including a selection tool;
• display a live video depicting at least one individual in the viewing window of the user interface;
• generate at least one segmentation mask for the at least one individual depicted in the live video, wherein each of the at least one segmentation mask comprises a body region of each individual and facial feature vectors of a facial region of each individual, wherein each facial feature vector is generated from facial features of each individual, wherein the facial feature vectors are derived by a facial recognition technique, and wherein a separate segmentation mask is generated for each individual, each separate segmentation mask comprising a body region and facial feature vectors of a facial region of a corresponding individual;
• obtain selection of at least one individual depicted in the live video based on operation of the selection tool to designate at least one selected facial feature vector corresponding to the selected at least one individual;
• compare facial feature vectors in a facial region of each of individuals depicted in the live video with the selected at least one facial feature vector corresponding to the selected at least one individual;
• convert the segmentation masks of individuals with a corresponding body region to a filter mask when the facial feature vectors do not match the selected facial feature vector;
• composite the filter mask comprising facial feature vectors that do not match the selected facial feature vector with a background content of the live video to generate composited background content filtering entire individuals corresponding to the facial features vectors that do not match the selected facial feature vector, wherein filtering entire individuals comprises causing both a body region and a facial region of each individual to be hidden from view in the viewing window;
• apply a graphical effect to the composited background content;
• and
• display a modified video comprising the segmentation mask and the composited background content when the selected at least one individual is in a field of view of the webcam.