Q-SYS VisionSuite: Seervision Technology

The most challenging thing about a scenario like this,

which is presenter tracking,

is that in a remote training environment,

you want the presenter not to be nailed to the floor at the podium.

You want him to be able to walk around and pontificate, and, you know, address questions.

Um, or in a collaboration experience, maybe you want to go to the Whiteboard

and take some notes and then return to your seat.

Uh, the moral of this story is you want to be able to capture all of those things,

and it might be outside of the watchful eye of a stationary predetermined scenario.

So that's why, uh, a little, uh, a couple of months ago,  

Q-SYS acquired a company called Seervision.

Now, what Seervision is, in a nutshell,  

is an AI accelerator that leverages computer vision-based scene analysis

and full body analysis to automatically follow and frame a presenter.

Now I'm not talking about just regular old, uh, you know, facial tracking,

and a lot of, there are a lot of facial tracking solutions out there.

I'm talking about a step above.

Um, we are doing full body analysis that is tracking  

things like my height and my clothing and my hair and my facial movements,

and it's synthesizing all of that in order to give me a full body experience

that's going to allow me to overcome some of the limitations of just facial features.

Like if I were to turn around and I walk across the camera,

it isn't losing me because it has other data points from which to drive that camera.