Great explanation Cyrill! Your videos are really good prepared and the train of thought is always well thought out! This really helps for learning and being ready to start CV projects! Continue your great work!
Cool! Thank you. So basically, knowing extrinsics and intrinsics of the camera, we can tell where a person is located in 3d space? Those 3d coordinates will be relative to the camera?
In general you estimate coordinates with respect to a Geodetic coordinate system. You do that by using a set of well-measured landmarks in the field (ground control points), measured by other, usually Geodetic, methods.