System and method for fewer or no non-participant framing and tracking

1 . A method, comprising:

detecting, by an electronic processor upon obtaining a video stream from a camera, a plurality of potential participants in an image from the video stream;

identifying, by the electronic processor upon detecting the plurality of potential participants in the image, a nonparticipant among the plurality of potential participants based on determining, by the electronic processor upon detecting a display screen in the image, that the display screen displays the nonparticipant, wherein determining that the display screen displays the nonparticipant comprises identifying, by the electronic processor, a boundary of the display screen; and

identifying, by the electronic processor, the display screen being activated based on a histogram of pixels within the boundary of the display screen, wherein the nonparticipant is identified in response to the identifying of the display screen being activated.

2 . The method of claim 1 ,

wherein the detecting the plurality of potential participants comprises:

detecting, by the electronic processor, a plurality of human heads corresponding to the plurality of potential participants; and

generating, by the electronic processor, a first bounding box corresponding to the nonparticipant, the first bounding box surrounding a first human head of the plurality of human heads for the nonparticipant, and

wherein the identifying of the boundary of the display screen including the nonparticipant comprises:

identifying, by the electronic processor, the boundary of the display screen entirely including the first bounding box.

3 . The method of claim 1 further comprising:

determining, by the electronic processor, a liveness indication of the nonparticipant, and

wherein the identifying of the nonparticipant comprises: identifying, by the electronic processor, the liveness indication of the nonparticipant being below a predetermined liveness threshold.

4 . The method of claim 3 , wherein the determining the liveness indication of the nonparticipant comprises:

converting, by the electronic processor, the nonparticipant to a grey scale image;

convolving, by the electronic processor, the grey scale image with a predetermined kernel; and

determining, by the electronic processor, a variance based on the convolved grey scale image, the variance being the liveness indication.

5 . The method of claim 3 , wherein the nonparticipant is a reflected image of a potential participant of the plurality of potential participants reflected on a reflective surface.

6 . The method of claim 1 further comprising:

splitting the image into a discarding area and an including area based on a wall location, and

wherein the identifying of the nonparticipant comprises:

identifying, by the electronic processor, the nonparticipant being included in the discarding area.

7 . The method of claim 6 further comprising:

receiving, by the electronic processor, a user input being indicative of the wall location.

8 . The method of claim 6 further comprising:

converting a three-dimensional space of the image into an x-y coordinate plane, an x-y coordinate plane including a plurality of x-y coordinates, each x-y coordinate being indicative of a distance from an imaging device,

wherein the wall location comprises a subset of the plurality of x-y coordinates, the subset defining the discarding area,

wherein the method further comprises:

determining, by the electronic processor, a first x-y coordinate of the plurality of x-y coordinates for the nonparticipant, and

wherein the identifying of the nonparticipant being included in the discarding area comprises:

identifying, by the electronic processor, the first x-y coordinate being included in the discarding area.

9 . The method of claim 1 , wherein a frame comprises a composite frame including a panel corresponding to another potential participant among the plurality of potential participants and excluding the nonparticipant.

10 . The method of claim 1 ,

wherein a frame comprises a group frame including another potential participant, and

wherein the nonparticipant is not processed to be included in the group frame.

11 . The method of claim 1 , further comprising:

discarding, by the electronic processor, the nonparticipant from the plurality of potential participants prior to framing the plurality of potential participants.

12 . The method of claim 1 , further comprising:

determining, within the image by the electronic processor, that the nonparticipant is located outside a defined spatial boundary within a field of view of the camera; and

identifying, by the electronic processor upon detecting the plurality of potential participants in the image, the nonparticipant among the plurality of potential participants based on the determining that the nonparticipant is located outside the defined spatial boundary within the field of view of the camera.

13 . The method of claim 12 , further comprising:

determining, within the image by the electronic processor, that liveness of the nonparticipant is below a predetermined threshold, and

identifying, by the electronic processor upon detecting the plurality of potential participants in the image, the nonparticipant among the plurality of potential participants based on the determining that the liveness of the nonparticipant is below the predetermined threshold.

14 . A system, comprising:

an imaging device;

a memory; and

an electronic processor coupled to the memory,

wherein the electronic processor is to:

detect, upon obtaining a video stream from the imaging device, a plurality of potential participants in an image from the imaging device; and

identify, upon detecting the plurality of potential participants in the image, a nonparticipant among the plurality of potential participants based on determining, upon detecting a display screen in the image, that the display screen displays the nonparticipant, wherein determining that the display screen displays the nonparticipant comprises identifying, by the electronic processor, a boundary of the display screen and wherein the detecting the plurality of potential participants comprises:

detecting, by the electronic processor, a plurality of human heads corresponding to the plurality of potential participants; and

generating, by the electronic processor, a first bounding box corresponding to the nonparticipant, the first bounding box surrounding a first human head of the plurality of human heads for the nonparticipant, and wherein the identifying of the boundary of the display screen including the nonparticipant comprises identifying, by the electronic processor, the boundary of the display screen entirely including the first bounding box.

15 . The system of claim 14 ,

wherein the electronic processor is further configured to:

determine a liveness indication of the nonparticipant, and

wherein to identify the nonparticipant, the electronic processor is configured to:

identify the liveness indication of the nonparticipant being below a predetermined liveness threshold.

16 . The system of claim 14 ,

wherein the electronic processor is further configured to:

split the image into a discarding area and a framing area based on a wall location, and

wherein to identify the nonparticipant, the electronic processor is configured to:

identify the nonparticipant being included in the discarding area.

17 . The system of claim 14 , wherein the electronic processor is further to:

determine, within the image by the electronic processor, that the nonparticipant is located outside a defined spatial boundary within a field of view of the imaging device; and

identify, by the electronic processor upon detecting the plurality of potential participants in the image, the nonparticipant among the plurality of potential participants based on the determining that the nonparticipant is located outside the defined spatial boundary within the field of view of the imaging device.

18 . A non-transitory computer-readable medium storing computer-executable code, comprising code for causing a computer to:

detect, upon obtaining a video stream from a camera, a plurality of potential participants in an image from the video stream; and

identify, upon detecting the plurality of potential participants in the image, a nonparticipant among the plurality of potential participants based on determining, upon detecting a display screen in the image, that the display screen displays the nonparticipant, wherein determining that the display screen displays the nonparticipant comprises identifying, a boundary of the display screen, and wherein the detecting the plurality of potential participants comprises:

detecting a plurality of human heads corresponding to the plurality of potential participants; and

generating a first bounding box corresponding to the nonparticipant, the first bounding box surrounding a first human head of the plurality of human heads for the nonparticipant, and wherein the identifying of the boundary of the display screen including the nonparticipant comprises identifying the boundary of the display screen entirely including the first bounding box.

19 . The non-transitory computer-readable medium of claim 18 ,

wherein the computer-executable code further causes the computer to:

determine a liveness indication of the nonparticipant, and

wherein to identify the nonparticipant, the computer-executable code causes the computer to:

identify the liveness indication of the nonparticipant being below a predetermined liveness threshold.

20 . The non-transitory computer-readable medium of claim 18 ,

wherein the computer-executable code further causes the computer to:

split the image into a discarding area and a framing area based on a wall location, and

wherein to identify the nonparticipant, the computer-executable code causes the computer to:

identify the nonparticipant being included in the discarding area.

21 . The non-transitory computer-readable medium of claim 18 , wherein the computer-executable code further causes the computer to:

discard the nonparticipant from the plurality of potential participants prior to framing the plurality of potential participants.

22 . The non-transitory computer-readable medium of claim 18 , wherein the computer-executable code further causes the computer to:

determine, within the image, that the nonparticipant is located outside a defined spatial boundary within a field of view of the imaging device; and

identify, upon detecting the plurality of potential participants in the image, the nonparticipant among the plurality of potential participants based on the determining that the nonparticipant is located outside the defined spatial boundary within the field of view of the imaging device.