Training Artificial Intelligence to perform real-life tasks has been painful. The latest AI services now offer more accessible user interfaces. These require little knowledge about machine learning. The Microsoft LUIS service (Language Understanding Intelligent Service) performs an amazing task: interpreting natural language sentences and extracting relevant parts. You only need to provide 5+ sample sentences per scenario.
In this article series, we’re creating a sample app that interprets assessments from vital signs checks in hospitals. It filters out relevant information like the measured temperature or pupillary response. Yet, it’s easy to extend the scenario to any other area.
The vision: automatic checklists, filled out by simply listening to users explaining what they observe. The architecture of the sample app is based on a lightweight architecture: HTML5, Node.js + the LUIS service in the cloud.
Such an app would be incredibly useful in a hospital, where nurses need to perform and log countless vital sign checks with patients every day.
In part 1 of the article, I’ve explained the overall architecture of the service. In this part, we get hands-on and start implementing the Node.js-based backend. It will ultimately handle all the central messaging. It communicates both with the client user interface running in a browser, as well as the Microsoft LUIS language understanding service in the Azure Cloud.
Creating the Node Backend
We don’t have a Christmas tree in our apartment. But in today’s world, this is what Augmented Reality is for, right? Therefore, I decided to create an AR Christmas Tree in 5 minutes. This also gave me an opportunity to check out the new Google ARCore Developer Preview 2.
Christmas Tree 3D Model
First off, you need a 3D model of a Christmas tree. Two of the most accessible sources are Google Poly and Microsoft Remix 3D. Sticking to models created directly by Google and Microsoft, these two are the choices:
During the last few years, cognitive services became immensely powerful. Especially interesting is natural language understanding. Using the latest tools, training the computer to understand real spoken sentences and to extract information is reduced to a matter of minutes. We as humans no longer need to learn how to speak with a computer; it simply understands us.
I’ll show how to use the Language Understanding Cognitive Service (LUIS) from Microsoft. The aim is to build an automated check-list for nurses working at hospitals. Every morning, they record the vital sign of every patient. At the same time, they document the measurements on paper checklists.
With the new app developed in this article, the process is much easier. While checking the vital signs, nurses usually talk to the patients about their assessments. The “Vital Signs Checklist” app filters out the relevant data (e.g., the temperature or the pupillary response) and marks it in a checklist. Nurses no longer have to pick up a pen to manually record the information.
ARCore has a great feature – light estimation. The ARCore SDK estimates the global lighting, which you can use as input for your own shaders to make the virtual objects fit in better with the captured real world. In this article, I’m taking a closer look at how the light estimation works in the current ARCore preview SDK.
Following the basic project setup of the first part of this article, we now get to the fascinating details of the ARCore SDK. Learn how to find and visualize planes. Additionally, I’ll show how to instantiate objects and how to anchor them to the real world using Unity.
ARCore by Google is still in preview and only runs on a select few phones including the Google Pixel 2. In this article, I’m creating a demo app for ARCore using the ARCore SDK for Unity (Preview 1).
It’s following up on the blog post series where I segmented a 3D model of the brain from an MRI image. Instead of following these steps, you can download the final model used in this article for free from Google Poly.
In the first part of the article, we captured a 360° photo using a Samsung Gear 360 camera. Now, we’ll create a new Unity project for Android. Using the right shader and material, we can assign the cylindric projection to a Skybox. This is the perfect 360° photo viewer for Unity, which can then be easily deployed to a Google Daydream / Cardboard VR headset!
Loading the 360° Photo in Unity
The Skybox in Unity is the easiest way to show a 360° photo in VR. Note that 360° 2D and 3D video will be supported out-of-the-box in the upcoming Unity 2017.3 release, according to the current Unity roadmap.
Update 13. November 2017: The latest source code of the Mixed Reality toolkit now combines both HoloLens and Mixed Reality headsets into a single toolkit that works with one Unity version: 2017.2.0p1 MRTP 4. It’s a special fork of Unity that is optimized for the “Mixed Reality Toolkit Preview”. A later version of Unity will hopefully combine all environments into a single release again. Read more about the environment setup at the GitHub pull request.
Update 19. October 2017: In the meantime, Unity 2017.2 final has been released, and the dev branch of the Mixerd Reality toolkit has been merged back to the master. You should now be fine using the following versions for HoloLens development: Unity 2017.2.0f3+, Mixed Reality Toolkit (master branch), Visual Studio 2017.+4, Windows 10.0.15063.0 SDK.
Original Article: Lately, the tools required for HoloLens / Mixed Reality development have been undergoing profound changes. All three tools involved in building HoloLens apps are being restructured:
Unity 2017 unifies Virtual / Augmented Reality APIs, making them flexible enough to target all platforms (e.g., phones with ARKit / ARCore, VR, AR). This also involves new and renamed APIs.
HoloToolkit has been renamed to Mixed Reality Toolkit, as Microsoft expands the scope to include the new VR headsets with inside-out tracking going on sale this fall.
Visual Studio 2017.3 also introduced some major changes under the hood. This is combined with the C# engine used in Unity slowly being migrated from the old Mono runtime to more recent versions of C#.