Microsoft has announced a $249 “Vision AI Developer Kit, aimed at AI edge developers using Azure IoT Edge and Azure Machine Learning. The kit features an 8MP, 4K camera which runs Linux on Qualcomm’s 10nm, AI-enabled QCS603 SoC. The Vision AI Developer Kit incorporates Qualcomm’s Vision Intelligence Platform, which is infused into its QCS603 SoC, with Microsoft’s Azure IoT Edge service, built on the Azure IoT Hub. The platform also includes Vision Studio and Azure Machine Learning (AML) for building, training, and deploying machine learning models. The kit is manufactured by Altek, and which also makes a Linux-driven, QCS603-based IPC603 camera reference design based on the QCS603.
The Vision AI Developer Kit is labeled as an “end-to-end Azure enabled solution with real-time image processing locally on the edge device, and model training and management on Azure.” Microsoft says that the kit enables you “deploy vision models at the intelligent edge in minutes, regardless of your current machine learning skill level.”
Azure provides three development paths: “no-code” using Custom Vision; Azure Cognitive Service, custom models with Azure Machine Learning; and the Visual Studio Code IDE. Targeted at novices, Custom Vision assists users through the process of uploading data, training, and deploying customer vision models including image tagging. The Vision AI Developer Kit, allows users to use Azure IoT Hub to deploy a custom vision model directly to the kit.
For more advanced users, you can try the Azure Cognitive Service with visual drag and drop tools for AML development, and also use the kit’s extension for Visual Studio Code, which offers sample Python modules, pre-built Azure IoT deployment configurations, and Dockerfiles for container creation and deployment. The Visual Studio Code also helps in adding business logic to existing Azure solutions based on camera input sent through Azure IoT Hub to transform the image data into normalized data streams using Azure Stream Analytics. The quad-core QCS603 on the Microsoft kit offers only 2x of the 1.7GHz “Silver” cores instead of six. The chips are part of the Qualcomm AI Engine built around Qualcomm’s Snapdragon Neural Processing Engine (NPE) software framework, that enables analysis, optimization, and debugging tools for developing with Tensorflow, Caffe, and Caffe2 frameworks. The Vision AI Developer Kit is built around Qualcomm’s Altek-built Vision Intelligence 300 Platform, also known as the EIC MS Vision 500 smart camera.
The device complements the Yocto Linux driven QCS603 SoC with 4GB LPDDR4. Storage option includes 16GB eMMC and a microSD slot. The centerpiece of the device is an 8-megapixel camera that features 4K UHD support and a four-microphone array. The device is also equipped with dual-band 802.11b/g/n radio, audio I/O jacks, an HDMI port, and LEDs. Power features include a USB Type-C port and a 1550mAh battery. The base of the device can swivel, enabling it has multiple mounting options.