AD-VEGA-320

m.2 Edge AI Module with one Intel® Movidius™ Myriad™ X VPU onboard

Anewtech Edge AI Module AD-VEGA-320 Advantech AI Accelerator Card

Features

  • Intel® Movidius™ Myriad™ X VPU onboard
  • Ultra compact, Low power consumption
  • Hardware acceleration for common deep neural networks
  • Scalable for multi video streams edge inference
  • 10 times the performance compared to previous generation
  • Intel® OpenVINO™ toolkit fully supported

Datasheet

Specification

Model VEGA-320-01A1
Processor
SOC one Myriad X MA2485
Form Factor
Form Factor M.2 2230 (Key A+E)
Dimensions
Dimensions (W x H x D) 22mm x 30mm x 3.63mm
Interface
Signal Interface PCIe Gen2 x1, USB 2.0
Environment
Temperature (Operating) 0~45°C, with 0.7 m/s air flow
Power Consumption
Power Consumption 3.8W
Cooling
Cooling Passive cooling
Operating System
Others Windows 10 Enterprise 64 bit, Ubuntu 16.04.3 LTS (64 bit), CentOS 7.4 (64 bit)
OpenVINO
OpenVINO OpenVINO R1 2019 or latest
Framework Support
Framework Support TensorFlow, Caffe

Application: AI-Powered Smart Street Lights

Anewtech-m2-ai-module-AD-VEGA-320-Advantech AI Accelerator Card

Cities are illuminated by thousands of streetlights that help drivers and pedestrians find their way home safely. Equipped with AI technology, streetlights can be used to not only light up roads, but also support city services such as air quality, humidity, and temperature monitoring, as well as traffic and parking management.

 

The customer had already implemented  edge computing platform to serve as a gateway computer for collecting data, including temperature and humidity levels, to facilitate operational analysis. Recently, the platform was upgraded with AD-VEGA-320 edge AI acceleration modules embedded into the cameras for analyzing multiple streams of video data and handling real-time tasks such as locating available parking spaces. The customer estimated that this solution increases the utilization of roadside parking by at least 10% to 15%.

  • Key Benefit
  • Compact, low-power design with minimal installation effort
  • Video analysis at the edge for instant response
  • Saves bandwidth resources and costs

Anewtech edge-AI-accelerater-card Advantech Singapore

Edge AI Suite Built-in

With Intel’s Distribution of OpenVINO™ toolkit and pre-trained models integrated, Edge AI Suite provides a deep learning model optimizer, an inference engine, pre-trained models, and a friendly GUI toolkit.

Anewtech-edge-ai-pc-openvino-toolkit-Advantech AI Accelerator Card Anewtech-edge-ai-pc-model-Advantech AI Accelerator Card Anewtech-edge-ai-pc-embedded-Advantech AI Accelerator Card Anewtech-edge-ai-pc-sdk-Advantech AI Accelerator Card
OpenVINO Toolkit Pre-trained Models Deployment Wizard 3rd Party AI SDK
  • OpenVINO R3.1 integrated
  • Boosted inference performance
  • Heterogeneous executions across CPU/VPU/GPU to optimize workload
  • Rapid object detection
    (YOLOv3)
  • Facial recognition
  • Human pose estimation
  • Quick start tutorial
  • Supports various deep learning frameworks
  • CPU/VPU/Memory monitoring
  • Facial recognition
  • Vehicle classification
  • License plate recognition