UPDATED 15:45 EDT / FEBRUARY 25 2019

EMERGING TECH

Microsoft’s new Azure Kinect DK sensor brings machine learning to the edge

The HoloLens 2 isn’t the only new product that Microsoft Corp. introduced at the Mobile World Congress in Barcelona Sunday night. The company also debuted the Azure Kinect DK, a cloud-connected sensor that can perform complex tasks such checking components coming off a production line for flaws.

The system (pictured) is the third evolution of a product that was initially sold as a video game accessory. Microsoft discontinued the original version in 2015 and repurposed the underlying technology, turning into it an enterprise device capable of running artificial intelligence algorithms. The Azure Kinect DK significantly expands upon these features in a smaller, lighter form factor.

Microsoft has equipped the device with a powerful 12-megapixel camera, a depth sensor and a seven-microphone array that picks up sound in 360 degrees. There’s also an accelerometer and a gyroscope. And a set of ports on the back make it possible to connect Azure Kinect DK units in the same location with one another to synchronize data collection.

The device sends sensory data to Microsoft’s Azure cloud platform, where enterprises can analyze it using the various managed AI services offered by the technology giant. This integration lends itself to a fairly broad spectrum of use cases.

One early adopter, Nebraska-based healthcare startup Ocuvera Inc., is harnessing Azure Kinect DK to help hospitals automatically detect when a patient falls. Another startup called Datamesh Consulting LLC is using the Azure Kinect DK to perform automated quality assurance at plants. Datamesh is also using the onboard camera to create 3-D model of objects for augmented and virtual reality applications.

That use case is not necessarily the primary purpose for which Azure Kinect DK was designed, but the device does have a role in Microsoft’s mixed reality strategy. It shares a depth sensor with the HoloLens 2 and can work in tandem with a pair of new mixed-reality services that the company debuted at MWC.

The first, Azure Spatial Anchors, is designed to simplify the creation of multi-user augmented reality applications. It uses camera footage from devices such as the Azure Kinect DK to make sure that virtual objects show up where they’re supposed to for every participant. A manufacturer, for instance, could use the service to overlay maintenance data on a feed of industrial robots in a factory and stream the video to a technician’s iPhone.

Microsoft’s other new cloud-based mixed reality offering is Azure Remote Rendering. The service provides an environment for rendering virtual objects such as building schematics that are too complex to generate locally on a user’s HoloLens or desktop.

Photo: Microsoft

A message from John Furrier, co-founder of SiliconANGLE:

Your vote of support is important to us and it helps us keep the content FREE.

One click below supports our mission to provide free, deep, and relevant content.  

Join our community on YouTube

Join the community that includes more than 15,000 #CubeAlumni experts, including Amazon.com CEO Andy Jassy, Dell Technologies founder and CEO Michael Dell, Intel CEO Pat Gelsinger, and many more luminaries and experts.

“TheCUBE is an important partner to the industry. You guys really are a part of our events and we really appreciate you coming and I know people appreciate the content you create as well” – Andy Jassy

THANK YOU