NVIDIA and Microsoft Create Edge-to-Cloud Real-Time Streaming Video Analytics Solution

Make cities smarter by connecting NVIDIA DeepStream Edge AI and Microsoft Azure IoT.
by Saurabh Jain

It’s a huge challenge extracting actionable insights from the sea of data created by the world’s billions of cameras and sensors.

Bringing all this raw data to the cloud is inefficient because of bandwidth, cost and latency limitations. So NVIDIA and Microsoft are making it possible to process it at the edge.

The companies have integrated NVIDIA DeepStream and Microsoft Azure IoT Edge to enable real-time streaming and video analytics that extract powerful insights from thousands of cameras distributed over wide areas.

How DeepStream and Azure IoT Edge Work Together

The DeepStream SDK is a scalable framework to build high-performance streaming analytics applications and then deploy them on NVIDIA GPU platforms.

Microsoft Azure IoT Edge is a fully managed service that delivers cloud intelligence locally to enable the remote monitoring and management of NVIDIA-powered devices. Azure IoT Edge deploys applications and services built using DeepStream from the cloud to run on these edge devices.

Combining these powerful technologies brings device management, monitoring and custom business logic to millions of edge devices for real-time insights and easy deployment. This makes it easier than ever to detect and classify objects, recognize patterns and identify anomalies.

DeepStream and Microsoft Azure IoT Edge generate situational awareness over large-scale physical infrastructures such as underground parking garages, malls, smart factories and city-wide road networks through real-time streaming analytics.

See This Collaboration in Action at GTC 2019

At GTC in San Jose from March 18-21, Microsoft will be showing an early preview of DeepStream and Azure IoT Edge in booth 1122. Developers can learn more on Tuesday, March 19, at 9 a.m. PT during a DeepStream technical deep dive.

A DeepStream container supporting Azure IoT Edge will be available soon for developers in the Azure IoT Edge marketplace.