ADLINK Technology Vizi-AI™ Machine Vision AI Development Kit

ADLINK Technology Vizi-AI™ Machine Vision AI Development Kit combines plug-and-play hardware and software to provide a faster, simpler, and scalable starting point for AI-deployments at the edge. This development kit offers a perfect starting point for enterprise developers and data scientists to find business value by enabling easy deployment of their machine-learning models. The Vizi-AI™ development kit includes an Intel Atom^® based SMARC computer module with Intel^® Movidius™ Myriad X™ VPU (with neural-computer engine) and Intel^® Distribution of OpenVINO toolkit. Additionally, a 40-pin connector, ADLINK Edge™ software, ADLINK Edge™ Profile Builder, and ADLINK Edge™ Model Manager are also included.

The Vizi-AI industrial machine vision AI development kit incorporates a range of pre-built OpenVINO compatible Machine Learning (ML) models that can be used straight out of the box. The enterprise developers can easily connect to different image capture devices, deploy, and improve ML models to harness insight from vision data to optimize operational decision-making. This approach can then be scaled for industrial requirements using the same software but deployed on more powerful hardware as needed. The overall mechanism provides developers/customers the ultimate future-proofed flexibility.

Kit Contents

Vizi-AI
Power adapter (US/EU)
Image on Debian Linux
40-pin connector
Micro SD Card with Vizi-AI ADLINK Edge™ software:
- Provides enhanced functionality of OpenVINO through the ADLINK Data River™ enabling data to flow freely and securely
- ADLINK Edge™ Profile Builder:
  - Provides a simple, intuitive user experience to manage devices and applications
- ADLINK Edge™ Model Manager:
  - Enables users to add their own models to a pre-loaded selection for easy deployment
- ADLINK Edge™ Frame Streamer:
  - Reads in video and streams the individual frames over the ADLINK Data River
- ADLINK Edge™ Training Streamer:
  - Provides a scheduled images collection mechanism that can deliver the data via the FTP to anywhere you want it.
- ADLINK Edge™ AWS Model Streamer:
  - Downloads inference models from AWS and streams them over the ADLINK Data River
- ADLINK Edge™ Node-RED:
  - To read inferenced results from the ADLINK Data River

Features

Intel Atom^® based SMARC 2.0 computer module with Intel^® Movidius™ Myriad™ X VPU (with Neural Compute Engine):
- Dedicated hardware accelerator for on-device deep neural networks and computer vision applications
Intel Distribution of OpenVINO toolkit (includes accelerators):
- Optimizes deep learning workloads across Intel^® architecture
- Streamlines deployments from the edge to the cloud

Quicker time to collect model data
Easy to manage and update models
Simple Edge AI configuration
Effortless software integration and configuration
Smooth transfer to production

Specifications

System specification:
- Intel Atom^® x5-E3940 SOC CPU
- Intel^® Movidius™ VPU Myriad-X VPU
- Memory 4GB LPDDR4
- Storage 1 x MicroSD for external storage
Software:
- Operating System Linux (Debian 9.9)