Questions regarding the use of RGB and depth sensors in skeletal estimation

[remon-nomer66]

Hello everyone,
I have the following questions regarding skeletal estimation.
Please understand that this may be difficult to understand because of the forced translation of Japanese.

1. Is the Classical/AI skeletal estimation done using both RGB and depth sensors?
2. I understand that there are two types of skeletal estimation, classical and AI-based methods. Can you tell us about the environment and accuracy of each camera installation?Also, are there any papers on this topic?

I am examining whether I can use it in a medical setting. Thanks!