ARKit and ARCore - How does one detect with something from the real world "hits" your object?

Think if someone in real life waved their hand and hit the 3D object in AR, how would I detect that? I basically want to know when something crosses over the AR object so I can know that something “hit” it and react.

Can this be done? If so how?

It could have probably been done with Tango (because there are built-in depth sensors), but I don’t see how it would be done with ARKit or ARCore, since there isn’t actually actually any depth-sensing going on…

A workaround would be to have it to image detection on your hand at a specified distance, tell it the size/measurement, and then as the hand got bigger or smaller, the scale could approximate the depth/distance/z-buffer…

But I haven’t actually tried anything like that, not sure how doable (doable, maybe, but probably not built-in or easy) with these single-camera AR SDKs…

Thanks for the response. I have no clue how to even start with something like that but I’m assuming that image detection is probably not fast enough to detect quick moving images. I thinking my idea is not feasible at the moment with current tech.