Christian, It's nice of you to volunteer the hardware, software, and support personnel to test out auto-tracking in Yokohama! :) (if it wasn't obvious) Regards, -drc > On Jul 24, 2015, at 9:30 PM, Christian Huitema <huitema@xxxxxxxxxxxxx> wrote: > > On Friday, July 24, 2015, at 7:14 PM John C Klensin wrote: > >> Agreed, but that doesn't solve either the chair problem or the >> floor mic one. Those can be mitigated by the chair walking >> into the box rather than sitting and running the meeting and by >> people at the floor mics getting a lot better at announcing >> their names, but the realistic alternative is either a lot more >> panning or multiple cameras and switching, either of which >> require human attention. > > John, we are in 2015. Computer vision can definitely help tracking the speaker. You can find face tracking algorithms in many packages, including open source variants. Computer systems can easily track the speaker's face, crop the image around that, and send the speaker-focused image over the video. This is not rocket science. The pink box is obsolete. > > -- Christian Huitema > > >
Attachment:
signature.asc
Description: Message signed with OpenPGP using GPGMail