Production ready EdgeAI with Eclipse ioFog and Google Coral

on YouTube ↗47m

" summary

Live demo shows a TensorFlow Lite model pushed from a Coral Dev Board to a production Darcy camera with drag-and-drop deployment via Eclipse ioFog, requiring no code or model changes and moving from prototype to device in under ten minutes. ioFog 3.0 alpha exposes edge resources (detects Coral accelerators), a revamped UI and YAML templates for fleet rollout. Coral Edge TPU delivers up to ~2 TOPS at sub‑watt power and tens of FPS on real video, and the demo runs successfully.

AI-written summary · about

" chapters (11)

1. 0:00Introduction
2. 3:00Overview
3. 10:07Edge TPU
4. 14:29Eclipse Foundation
5. 15:26DataDriven Edge
6. 18:20Eclipse ioFog
7. 24:09Edge Compute Network
8. 27:19Demo Application
9. 33:19Deployment
10. 36:28Business Case
11. 40:09QA

" related talks

• 13mCoral: Expanding the edge AI landscapeBill Luan · Google I/O 2021
• 50mML and AI at the edge with Google Coral, EdgeTPU and Cloud PlatformMarkku Lepisto, Grant Likely, Tamas Daranyi · Linaro Tech Days 2020
• 45mIntroducing Google Coral: Building On-Device AIBill Luan · Google I/O 2019
• 16mIntroducing Coral Dev Board MicroBill Luan · Google I/O 2022
• 06mTop AI and ML announcementsLaurence Moroney · Google I/O 2022
• 55mEdgeAI - AI in the Palm of Your HandDon Ward · MidWest DevFest 2020
• 14mSafety and Occupancy with AIMarkku Lepisto · Google I/O 2021
• 59mML and the IoT: Living on the EdgeBrandon D Satrom · NDC Oslo 2019