MotionFlow: IP cameras become privacy-preserving activity sensors. YOLOv11-Pose on Metis classifies actions from pose geometry. Only structured state over MQTT, no video leaves the device. Running 24/7. Full source on GitHub. #EdgeAI #Privacy https://
eu1.hubs.ly/H0t23L70
@axeleraai
-
MotionFlow: Privacy-Preserving Activity Sensors with YOLOv11-Pose
By
–
-
A.B.C.: Automatically Catalog Your Library with AI
By
–
A.B.C. (AI Book Cataloguer): point a camera at your bookshelf, detect spines with YOLOv8s on Metis M.2, and catalog your library automatically. Built by community member Denovo on @orangepixunlong. Open source. #EdgeAI #ComputerVision 📚 eu1.hubs.ly/H0t23Vb0 [Translated from EN to English]
→ View original post on X — @axeleraai, 2026-04-06 10:30 UTC
-
CCTV Object Detection: Offloading Pi 5 to Metis Compute Board
By
–
Offloaded CCTV object detection from a Pi 5 to a Metis Compute Board. Pi fan stopped screaming. ~30 FPS across two 1080p cameras, ~196ms latency. Zone filtering, Home Assistant webhooks, phone snapshots in 1-2 seconds. Full tutorial + code. #HomeAssistant #EdgeAI 📹 eu1.hubs.ly/H0t23Nx0 @raspberry_pi
→ View original post on X — @axeleraai, 2026-04-03 13:45 UTC
-
Gesture-Controlled Racing Game with Hand Tracking Technology
By
–
Gesture-controlled racing, no controller needed. YOLO11n-pose-hands on Metis for 21-keypoint hand tracking. Tilt wrists to steer, fist to accelerate, open palm to brake. Works with any keyboard racing game. Built by Dilip.m. #EdgeAI #Gaming 🏎️ eu1.hubs.ly/H0t1WCm0
→ View original post on X — @axeleraai, 2026-04-02 15:52 UTC
-
Axelera AI Offers Confectionery Security Solution for KitKat
By
–
Our condolences to KitKat on the loss of 12 tons of inventory. It’s a tragedy that hits close to home (mostly because we really wanted one). We’ve realized that while our AI is great at security, surveillance & industrial automation, its highest calling might actually be "confectionery preservation." We’re ready to help guard the next shipment with on-site vision that doesn't blink, doesn't sleep, and most importantly, doesn't eat the evidence. #kitkatheist #StolenKitKatTracker #HaveABreak #EdgeAI
→ View original post on X — @axeleraai, 2026-04-01 21:11 UTC
-
Axelera AI and Almawave Partner for Multilingual Edge AI Solutions
By
–
Axelera AI together with Almawave Edge AI that speaks your language, wherever you are. That's what this partnership unlocks. Almawave, based in Rome and part of the Almaviva Group, has built Velvet, a family of multilingual large language models natively developed in Italy and available in 24 languages. We've signed a Memorandum of Understanding to bring those models to Axelera AI's enterprise edge hardware, starting with Metis. Velvet 2B is already available through the Voyager SDK model zoo today. Together, we're exploring optimization of multimodal workloads and joint go-to-market across smart cities, security, healthcare, telecommunications, and industrial applications. This partnership reflects something we believe in deeply: sovereign AI crafted in Europe, trusted by the world, running at the edge, tuned for real-world context. Almawave brings the multilingual intelligence. We bring the purpose-built hardware to run it efficiently where it matters. Multilingual. Multimodal. Built for the edge. #AxeleraAI #Almawave #EdgeAI #GenerativeAI #SovereignAI #LLM #EuropeanTech #DIMC #VoyagerSDK
→ View original post on X — @axeleraai, 2026-04-01 16:04 UTC
-
Axelera AI Demonstrates Advanced Edge AI with Metis Cards at ISC West
By
–
5 models. 48 AIPU cores. Two 8K streams. Real time. At ISC West last week, we ran person-of-interest identification and weapon detection simultaneously using the Voyager SDK and three 4-chip Metis cards. 1,440+ model inferences/sec at 30-58W per card. The pilot phase of edge AI is over. Here's how we built it: eu1.hubs.ly/H0t6H2D0 #EdgeAI #ComputerVision #ISCWest
→ View original post on X — @axeleraai, 2026-04-01 13:00 UTC
-
YOLOv10n and Gesture Recognition on Metis Processor without GPU
By
–
Rock Paper Scissors Lizard Spock against Sheldon Cooper, running on Metis at 214 TOPS. YOLOv10n on HaGRID (1M+ gesture images), quantized for the AIPU. No GPU, no cloud. Built by community member Dilip. Bazinga. 🖖 #EdgeAI #YOLO eu1.hubs.ly/H0t21Bs0 [Translated from EN to English]
→ View original post on X — @axeleraai, 2026-04-01 08:15 UTC
-
Ultralytics YOLO Models Export Integration for Metis AIPUs
By
–
From trained model to edge deployment in days, not months. Ultralytics has introduced an updated export integration for Metis AIPUs. Export your YOLO models, compile for Metis hardware, and run inference without PyTorch at the edge. >> Join us on April 8 for an Ultralytics Live session where we'll walk through the integration in action. Stay tuned for details! >> Check out the blog here: eu1.hubs.ly/H0t6rj40 #AxeleraAI #Ultralytics #YOLO #EdgeAI #ComputerVision
→ View original post on X — @axeleraai, 2026-03-31 14:44 UTC
-
Air Instrument Demo: Hand Tracking Piano and Drums on Metis
By
–
Play piano and drums with empty hands. Community member @dilip.m built an air instrument demo using hand pose tracking on Metis with Voyager SDK. All inference on-device. Great event demo for kids. #EdgeAI #HandTracking 🎹 eu1.hubs.ly/H0t21DX0
→ View original post on X — @axeleraai, 2026-03-31 09:00 UTC