Systems and methods for presence-aware repositioning and reframing in video conferencing
Systems and methods are described herein for automatically reframing a video for a conference participant. Video of the participant is captured, and a first position of the participant is detected. An offset for the first position of the participant is then calculated to determine a relative distance from the center of the video frame. The captured video is modified based on the offset and is then presented in the video conference.
1 . A method for automatically reframing video conference participants in a video stream of a video conference, the method comprising:
capturing video;
generating a pixel coordinate array for each respective frame of the video;
detecting within a first frame of the video, a plurality of participants, wherein the plurality of participants comprises a left-most participant and a right-most participant;
determining a left-most pixel area corresponding to the left-most participant and a right-most pixel area corresponding to the right-most participant, wherein the left-most pixel area and the right-most pixel area are both based on the pixel coordinate array;
calculating a group center based on the left-most pixel area and the right-most pixel area, wherein the group center is quantified using pixels from the pixel coordinate array;
modifying subsequent frames of the video based on the group center; and
presenting the modified subsequent frames of the video.
2 . The method of claim 1 , wherein modifying the subsequent frames of the video based on the group center further comprises:
translating a position of each participant of the plurality of participants to a new position corresponding to the group center of the first frame.
3 . The method of claim 2 , wherein translating the position of each participant of the plurality of participants to the new position corresponding to the group center of the first frame comprises:
calculating a translation vector; and
for each frame of the video, applying the translation vector to each pixel of a plurality of pixels of the respective frame that form an image of each participant.
4 . The method of claim 1 , wherein modifying the subsequent frames of the video based on the group center further comprises cropping the video so that the video is centered at the group center.
5 . The method of claim 1 , further comprising:
encoding a media stream including the video with the modified subsequent frames; and
transmitting, to a video conference server, the media stream.
6 . The method of claim 1 , further comprising:
encoding a media stream including the video and the group center;
modifying the video to incorporate the modified subsequent frames; and
transmitting, to a video conference server, the media stream.
7 . The method of claim 6 , wherein presenting the modified subsequent frames of the video further comprises:
retrieving, at the video conference server, from the media stream, the group center;
cropping, at the video conference server, the video based on the group center;
reencoding, at the video conference server, the cropped video in a second media stream; and
transmitting, from the video conference server, the second media stream to client devices associated with each participant in the video conference.
8 . The method of claim 1 , further comprising:
determining a first resolution of the video;
determining a second resolution to which to scale the video to fit in a video conference layout; and
scaling the video to the second resolution.
9 . The method of claim 1 , further comprising:
based on determining that a change in one or more of the left-most pixel area and the right-most pixel area is greater than a threshold amount, altering the group center.
10 . The method of claim 1 , wherein the group center is a midpoint between the positions of each detected participant.
11 . A system for automatically reframing video conference participants in a video stream of a video conference, the system comprising:
video capture circuitry configured to capture video;
input/output circuitry; and
control circuitry configured to:
generate a pixel coordinate array for each respective frame of the video;
detect within a first frame of the video, a plurality of participants, wherein the plurality of participants comprises a left-most participant and a right-most participant;
determine a left-most pixel area corresponding to the left-most participant and a right-most pixel area corresponding to the right-most participant, wherein the left-most pixel area and the right-most pixel area are both based on the pixel coordinate array;
calculate a group center based on the left-most pixel area and the right-most pixel area, wherein the group center is quantified using pixels from the pixel coordinate array;
modify subsequent frames of the video based on the group center; and
present the modified subsequent frames of the video.
12 . The system of claim 11 , wherein the control circuitry configured to modify the subsequent frames of the video based on the group center is further configured to:
translate a position of each participant of the plurality of participants to a new position corresponding to the group center of the first frame.
13 . The system of claim 12 , wherein the control circuitry configured to translate the position of each participant of the plurality of participants to the new position corresponding to the group center of the first frame is further configured to:
calculate a translation vector; and
for each frame of the video, apply the translation vector to each pixel of a plurality of pixels of the respective frame that form an image of each participant.
14 . The system of claim 11 , wherein the control circuitry configured to modify the subsequent frames of the video based on the group center is further configured to crop the video so that the video is centered at the group center.
15 . The system of claim 11 , wherein the control circuitry is further configured to:
encode a media stream including the video with the modified subsequent frames; and
transmit, to a video conference server, the media stream.
16 . The system of claim 11 , wherein the control circuitry is further configured to:
encode a media stream including the video and the group center;
modify the video to incorporate the modified subsequent frames; and
transmit, to a video conference server, the media stream.
17 . The system of claim 16 , wherein the control circuitry configured to present the modified subsequent frames of the video is further configured to:
retrieve, at the video conference server, from the media stream, the group center;
crop, at the video conference server, the video based on the group center;
reencode, at the video conference server, the cropped video in a second media stream; and
transmit, from the video conference server, the second media stream to client devices associated with each participant in the video conference.
18 . The system of claim 11 , wherein the control circuitry is further configured to:
determine a first resolution of the video;
determine a second resolution to which to scale the video to fit in a video conference layout; and
scale the video to the second resolution.
19 . The system of claim 11 , wherein the control circuitry is further configured to:
based on determining that a change in one or more of the left-most pixel area and the right-most pixel area is greater than a threshold amount, alter the group center.
20 . The system of claim 11 , wherein the group center is a midpoint between the positions of each detected participant.