Track user in GLTF rooms


I was wondering what would be the best way to track in which room is a user in a given virtual house made out of GLTF models?

If I need to track how long a user is on the kitchen, or the living room, would collision detection be a good way to do this? And if so, do you have any recommendation, resources, on how to best apply collision detection in a world where each room is a GLTF model?

I wonder if maybe getting the x and z coordinates where the camera is moving in the world would be enough?

Thank you in advance, as usual.