Microsoft/Qualcomm Vision AI Developer Kit for IoT Development Goes GA -- ADTmag

Microsoft/Qualcomm Vision AI Developer Kit for IoT Development Goes GA

By Richard Seeley
September 4, 2019

Microsoft on Tuesday announced the general availability of the Vision AI Developer Kit, including a camera, which uses Qualcomm's Vision Intelligence 300 Platform, and the software needed to develop intelligent edge solutions using Azure IoT Edge and Azure Machine Learning.

"It supports an end-to-end Azure enabled solution with real-time image processing locally on the edge device, and model training and management on Azure," according to a blog posted Tuesday by Anne Yang, principal PM manager at Microsoft. "The Vision AI Developer Kit, made by our partner eInfochips, can now be ordered from Arrow Electronics."

With the Qualcomm camera, IoT devices could be used as a workplace safety monitor checking whether construction workers are wearing their hardhats on the job, or it could perform routine inventory management by checking if products are stocked on shelves, Yang explained. With advancements in IoT technology it is possible to relay images from the edge via the cloud to downstream applications providing alerts of unsafe working conditions or empty store shelves.

Yang outlined three options for developers to get started:

No code using Custom Vision, an Azure Cognitive Service
Custom models with Azure Machine Learning
Fully integrated development environment provided by Visual Studio Code

"The Vision AI Developer Kit integration with Custom Vision includes the ability to use Azure IoT Hub to deploy your custom vision model directly to the developer kit," Yang wrote. "These custom vision models are then accelerated using the camera's Snapdragon Neural Processing Engine (SNPE), which enables image classification to run quickly even when offline."

Data scientists can use Azure Machine Learning with the kit to create models that can be deployed to the Qualcomm camera, she explained.

"Visual Studio Code provides developers a single development environment to manage their code and access Azure services through plugins," Yang writes. "For developers using Visual Studio Code, we have created a GitHub repository which includes sample Python modules, pre-built Azure IoT deployment configurations, and Dockerfiles for container creation and deployment. You can use Visual Studio Code to modify the sample modules or create your own and containerize them to deploy on the camera."

The Vision AI DevKit extension can be installed for the Visual Studio Code development environment where developers can use it to deploy modules and work with the Azure IoT Hub, according to Microsoft.

"You can also leverage Visual Studio Code to add business logic to your own Azure solutions that consume information from the camera using IoT Hub and transform camera data into normalized data streams using Azure Stream Analytics," Yang explained.

More information is available on the Vision AI Developer Kit GitHub page.