Transcript
Q-SYS VisionSuite: Seervision Technology
2m 50s
00:00
The most challenging thing about a scenario like this,
00:03
which is presenter tracking,
00:04
is that in a remote training environment,
00:07
you want the presenter not to be nailed to the floor at the podium.
00:10
You want him to be able to walk around and pontificate, and, you know, address questions.
00:17
Um, or in a collaboration experience, maybe you want to go to the Whiteboard
00:21
and take some notes and then return to your seat.
00:23
Uh, the moral of this story is you want to be able to capture all of those things,
00:29
and it might be outside of the watchful eye of a stationary predetermined scenario.
00:33
So that's why, uh, a little, uh, a couple of months ago,
00:37
Q-SYS acquired a company called Seervision.
00:41
Now, what Seervision is, in a nutshell,
00:43
is an AI accelerator that leverages computer vision-based scene analysis
00:48
and full body analysis to automatically follow and frame a presenter.
00:54
Now I'm not talking about just regular old, uh, you know, facial tracking,
00:59
and a lot of, there are a lot of facial tracking solutions out there.
01:02
I'm talking about a step above.
01:04
Um, we are doing full body analysis that is tracking
01:08
things like my height and my clothing and my hair and my facial movements,
01:15
and it's synthesizing all of that in order to give me a full body experience
01:20
that's going to allow me to overcome some of the limitations of just facial features.
01:25
Like if I were to turn around and I walk across the camera,
01:30
it isn't losing me because it has other data points from which to drive that camera.