Accurately calibrate CAD overlay model in ARKit

Hi,

I'm looking for some ideas from the community on how to approach the below described task:


I have a 3D CAD model, which I use in ARKit and overlay with the real-world model. So far so good, all works.. but I'd like to improve the accuracy of the overlay by positioning the 3D CAD model according to some 'calibration' feature points in the real world, e.g. notches/features besides the real model. This would allow the CAD model to scale and align correctly and continuously to the real model.


Now, of course ARKit has its rawFeaturePoints to align the virtual world with the real world. But how could I force feature points at the 'calibration' feature points, and identify them for orientation of the 3D CAD model... Any other ideas, approaches to achieve the task described above.


Thanks!


Cujo

Replies

Hi Cujo,

My organisation Ghyston is looking at a similar problem at the moment. Some ideas might be to use QR codes and the Vision framework to track the object. The QR codes could be in a fixed position attached to the real model providing a relatively simple way to track the object's movement, but I'm not sure if it would be precise enough for you.

A more involved solution might be to take a sample point cloud from the real world model and then use an algorithm like ICP to map it to your CAD model, but again if the point cloud is not particularly accurate I'm not sure if that would benefit you either.

The iPhone 7/8 Plus / X include dual cameras and might provide better results too (if you're using an older model at the moment). Camera specs can be seen here:

https://developer.apple.com/library/content/documentation/DeviceInformation/Reference/iOSDeviceCompatibility/Cameras/Cameras.html

If you'd be interested in working with us to achieve higher (mm) accuracy with AR, please contact me / Ghyston.

Good luck!

Michael

Thanks Michael , I’ve send you a direct message to your company info address. Thanks

I've attempted tracking using QR Codes and the recognition of the code and it's embedded value is fast and accurate. But the accuracy of reprojecting the QR Code marker position and orientation isn't accurate or consistent at the moment. It's a little better if the QR Code is located on a horizontal surface.


Point cloud mapping is also a bit tricky from what I've tried.


I'm hoping to have object recognition built into the system which would allow for mapping to a model and allowing for alignment of the scene.

Is this the sort of things you guys are looking to do? https://www.youtube.com/watch?v=6W7_ZssUTDQ


Vuforia has accurate 3D model recognition + tracking so you can overlay content ontop of objects based on their CAD data. These features should be available this month.


(I work for Vuforia)

Hi vad710,

i just saw this video of the vuforia overlapping. I am currently working on a simular app, is there any tutorial, where you are guided to create an app like this?


Best regards

Tobi