OnQ Blog

Qualcomm Vision Intelligence Platform + Microsoft Azure bring edge AI solution

Today Qualcomm Technologies and Microsoft announced that they are working together to help customers and developers quickly create IoT solutions like home monitoring cameras, enterprise security cameras and smart home devices that use on-device vision artificial intelligence (AI) in retail, manufacturing, logistics applications and more.

A key element of this work will be a Vision AI developer kit. The kit is intended to combine the hardware and software required to deliver intelligence at the edge along with integration of Azure Machine Learning and Azure IoT Edge. It uses the Qualcomm Visual Intelligence Platform and Azure Machine Learning to support advance AI capabilities right to the camera, all while being centrally managed from Azure. To support this, the developer kit runs Azure IoT Edge, which allows Azure Machine Learning Models to be deployed from Azure to the kit. Azure IoT Edge also supports local deployment and execution of custom code and other Azure Services, such as Azure Stream Analytics and Azure Cognitive Services, which can be downloaded from the Azure cloud platform to run locally on the edge.

View high-res image

Evolving edge AI and cloud AI architecture for the IoT

The developer kit builds on the best of both companies’ strengths so customers can innovate and break new ground. Microsoft’s Azure ML can generate models from Azure cognitive services that run on the Qualcomm Vision Intelligence Platform for on-device edge AI compute that is supported by Azure IoT Edge for efficient deployment and connected device management capabilities.

Applying AI for IoT use cases for on-device visual and audio analytics requires energy efficient compute to make intelligent decisions in real time. The Qualcomm Vision Intelligence Platform brings in its signature Artificial Intelligence Engine with heterogenous architecture to enable energy efficient performance and computing. Qualcomm Snapdragon Neural Processing Engine (NPE) SDK in conjunction with Microsoft’s Azure Machine Learning is designed to support optimized AI models for the Vision Intelligence Platform. The result is edge computing for AI and cognitive services, while offering exceptional power and thermal efficiency for a superior user experience.

Edge AI benefits for the IoT ecosystem

The Vision Intelligence Platform developer kit that includes both hardware and software, helps customers and developers innovate by unlocking the benefits of AI at the edge:

  • Low latency
  • Superior robustness
  • Privacy
  • Efficient utilization of network bandwidth
  • Efficient utilization of cloud resources

Azure benefits for the IoT ecosystem

Azure IoT Edge along with Azure ML will provide services for managing edge devices and allow developers to build ML solutions with access to pretrained models and customization of AI models

  • Cloud storage
  • Cloud processing
  • Enhanced security
  • Enhance device provisioning and management
  • Integrated environment to build, train, validate and deploy AI models on edge devices
  • Device telemetry and analytics

In particular, Qualcomm Technologies and Microsoft will be working in parallel to make sure the Snapdragon NPE interoperates with Azure services, so customers and developers can convert their models and deploy them to the Azure IoT Edge running on the Qualcomm Vision Intelligence Platform.

View high-res image

The vision developer kit, based on the Vision Intelligence Platform powered by the Qualcomm AI Engine, is expected to be available later this year.

Stay tuned for more ways to build AI and edge computing into your IoT solutions.

Qualcomm Vision Intelligence Platform, Qualcomm AI Engine, Qualcomm Snapdragon, and Qualcomm Neural Processing Engine are products of Qualcomm Technologies, Inc. and/or its subsidiaries

 

Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries ("Qualcomm"). Qualcomm products mentioned within this post are offered by Qualcomm Technologies, Inc. and/or its subsidiaries. The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.