Tata Elxsi's IRIS: edge filtering cuts cloud frames 70-80% for real-time factory safety AI
AWS ML Blog · rss · 2026-09-22
AWS ML Blog details Tata Elxsi's IRIS industrial safety platform on AWS. Edge servers (Greengrass + Jetson AGX Orin) extract 2-5 fps frames and filter 70-80% before upload; only <1KB metadata events flow through Kinesis (2,000-5,000 eps, p95 <200ms). SageMaker endpoints per model family (YOLOv8 PPE detection, polygon geofencing, SlowFast action recognition, monocular-depth vehicle proximity) run on ml.g5.xlarge at 40-60 RPS with p95 <300ms, scaled by target tracking plus SQS queue-depth policies and 4-8 frame micro-batches. A fully serverless, event-driven blueprint decoupling image and metadata paths.
More from Infra
- H Company trains computer-use agents on SkyPilot: thousands of sub-second sandboxes — skypilot_org · 2026-09-23
- MiniMax H3 video gen runs locally on M5 Ultra: 768p in ~2m22s with optimizations — bakawolf123 · 2026-09-22
- Cisco: Agentic AI to Drive 9X Enterprise Traffic Growth by 2035 vs 2.5X Without — Beth_Kindig · 2026-09-22
- Cloudflare ships Vary support in Cache Rules to tame HTTP's 'ugliest' header — threepointone · 2026-09-22
- Skipping failed pipeline stages during training: near-baseline loss at 1% failure rate — covenant_ai · 2026-09-22
- Fluidstack breaks ground on $4B Texas data center campus planned for up to 1.5 GW — MxMnr · 2026-09-22