iTwin.js
Published in

iTwin.js

Classified

“I don’t know how to create a digital twin.

I have no 3d design experience!”

Do you know how to draw a box?

“Of course!”

Then you know how to create a digital twin.

Introducing Classifiers

For those of you not privy to the process of creating a digital twin, it can take tremendous amounts of effort, money, (and the ever so fleeting) time. Especially if you are a beginner at 3D design like myself. Every time I have attempted to use a design tool like MicroStation or Revit, I goof around with the controls, draw a couple of carefully positioned boxes, pause, ponder…and hit the “X” on the top right of my screen in quiet resignation.

Alas, my pursuit of creating a digital twin continues to remain a pipe dream.

Lucky for me — and for the infrastructure industry at large — there is a better solution. In fact, it might be the finest solution I have encountered thus far. As mentioned in a previous post, the process of creating your digital twin can be supercharged by using the magic of reality data.

It allows you to literally take photos of entire infrastructure assets— such as windfarms, roadways, buildings, cities, and even your living room table — and conjure up a 3D model out of them. Speaking of living room tables…I decorated mine just for the sake of this example. I’m calling it — Table City

…made out of candles, shot glasses, flying Starbucks cups, and other fun stuff. If the back of your head is still intact, allow me to blow it.

All I did was turn on video mode on my iPhone, walk around my living room, push the video into our reality modeling software, and let it do the heavy lifting of extracting images and generating the 3D mesh you see above. Then I simply pulled it into MicroStation…and now I am a huge step closer to my dream of creating a digital twin.

We are almost there! But not quite.

As you can see above, our digital twin (although good looking) is just a blob of 3D data. There’s no way for us to select individual elements (such as a candle or shot glass) and show their properties. For example, what does the shot glass represent? Is it a tree? Is it a building?

Sadly, without such classification, our digital twin will never be taken seriously. Yes, its got the looks…but no personality :-/

Enter Classifiers!

Classifiers give us a quick and easy way to draw simple shapes (such as boxes, circles, spheres) on top of our 3D blob to separate out individual elements, identify them, and add business properties.

Here’s where your box-drawing skills can shine.

Allow me to demonstrate by adding some panache to Table City.

Some of you may be wondering — would this work on an actual city, or just made-up ones contrived from household objects? To address that healthy skepticism, here’s an example of classifiers being used on the entire city of Philadelphia. The sample also contains code for using classifiers within your own iTwin.js application.

And as for our made-up Table City…being its proud and only citizen, I henceforth declare it as successfully:

-Roop, reporting live from the basement.

P.S. Click here for a deeper dive into classifiers.

P.P.S. Many thanks to Kurt Rasmussen for his guidance on capturing reality data. If you would like similar guidance or are curious about our reality data trial, please contact us here.

<- previous post | home | next post ->

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store