ARSkelton3D Documentation - Motion Capture, iPadOS 13 beta

Question

ericfrommorgan hill OP

Created Jul ’19

Replies 1

Boosts 0

Participants 2

Hi Guys,

I have been playing around with the new Motion Capture stuff in ARKit 3 and there are couple things I don't see in the documentation and am hoping people can help fill in the gaps for me.

It looks like the jointModelTransform returns a 4X4 matrix. What is in this? I see in the "Capturing Body Motion in 3D" sample code that it looks like cloumn 3 has the 3d coordinates but what are the other items? (https://developer.apple.com/documentation/arkit/arskeleton3d/3295992-jointmodeltransforms)
Is there a confidence metric for joint identification that is available somewhere within ARSkelton3d?

Boost

Answer 1

DandyLyons OP

Jun ’21

I don't know much about it but apparently, a 4X4 matrix is pretty standard for anything having to do with 3D models.

https://math.stackexchange.com/questions/336/why-are-3d-transformation-matrices-4-times-4-instead-of-3-times-3

0