BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:GStreamer as a Foundation for Vision AI Edge Solutions
DTSTART;VALUE=DATE-TIME:20261010T121500Z
DTEND;VALUE=DATE-TIME:20261010T124500Z
DTSTAMP;VALUE=DATE-TIME:20261009T233406Z
UID:indico-contribution-597@indico.freedesktop.org
DESCRIPTION:Speakers: Tomasz Janczak (Intel Corporation)\nIn this talk\, w
 e will share our experience enabling production-grade Edge AI solutions on
  top of GStreamer. The discussion goes beyond building working video analy
 tics pipelines and focuses on what it takes to turn them into enterprise-r
 eady systems that can be deployed\, operated\, monitored\, and extended re
 liably at the edge. We will address this through two complementary dimensi
 ons: enterprise-grade deployment and the evolution of Vision AI from class
 ical computer vision toward VLM- and agentic AI-driven workflows.\n\nThe e
 nterprise-grade deployment dimension focuses on microservice-style operati
 on: dynamic stream and pipeline lifecycle management\, integration with ca
 meras and messaging infrastructure\, remote diagnostics\, latency tracing\
 , and operational observability.\n\nThe Vision AI dimension focuses on the
  evolution from traditional CV workloads toward VLM and agentic AI scenari
 os. These workloads introduce new requirements for AI model integration\, 
 external AI services\, dynamic pipeline reconfiguration\, event- or prompt
 -driven processing\, and short-term retention of selected data for retrosp
 ective analysis.\n\nRather than presenting a finished framework\, the talk
  is intended to open a community discussion: which capabilities should rem
 ain application-specific\, which could become reusable plugins or conventi
 ons\, and which gaps might be addressed in the GStreamer base repository o
 r surrounding ecosystem.\n\nProposed 30-minute timeline:\n5 min — Introd
 uction and background: why GStreamer is a strong foundation for Edge AI\, 
 and how Intel is using it today.\n10 min — Enterprise-grade deployment: 
 operating GStreamer-based pipelines as reliable edge services.\n10 min —
  Vision AI evolution: implications of CV\, VLM\, and agentic AI workflows 
 for model integration\, pipeline flexibility\, and GStreamer abstractions.
 \n5 min — Summary and Q&A: key takeaways and discussion points for reusa
 ble conventions\, plugins\, or base-repository additions.\n\nhttps://indic
 o.freedesktop.org/event/14/contributions/597/
LOCATION:Impact Hub Prague
URL:https://indico.freedesktop.org/event/14/contributions/597/
END:VEVENT
END:VCALENDAR