BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:How we are building a distributed multi-camera real-time sports tr
 acking system using GStreamer and Rust
DTSTART;VALUE=DATE-TIME:20230926T145000Z
DTEND;VALUE=DATE-TIME:20230926T152000Z
DTSTAMP;VALUE=DATE-TIME:20260716T235315Z
UID:indico-contribution-244@indico.freedesktop.org
DESCRIPTION:Speakers: Robin Gustavsson (Spiideo)\, Daniel Pendse (Spiideo)
 \nAt Spiideo we offer automated sports video solutions to our customers fo
 r recording\, analysis and broadcasting. We use a multi-camera setup to cr
 eate a stitched panoramic video with an AI assisted cameraman.\n\nThis tal
 k will showcase how we moved from a segment based system with a glass-to-g
 lass latency of almost two minutes to a frame-based system with a latency 
 of around three seconds.\n\nIn those three seconds we need to perform stit
 ching of multiple 4K streams\, detect objects in each camera stream and pr
 edict where to aim the virtual camera to follow the action on the pitch. A
 nd we do all of this across multiple instances in the cloud.\n\nThis was S
 piideo’s first real use of GStreamer and we will talk about what we stru
 ggled with\, what helped us (a lot) and what we still do not really (reall
 y) understand.\n\nhttps://indico.freedesktop.org/event/5/contributions/244
 /
LOCATION:Palexco Room 2
URL:https://indico.freedesktop.org/event/5/contributions/244/
END:VEVENT
END:VCALENDAR