OK - after this explanation - I suppose - they will be rather more interested by graphic details, some objects etc. For this they don't need any voice narration. So - in this case also this overview from the "fly" is better than look from the person walking around. And also You can forget about this X-ray. From view of person walking on the ground it's impossible show some roofs of houses' details etc. You have to show them and bring their attention at some details hardest to create , some curious objects etc. You know - the problem isn't how to make a good product - the problem is rather - how to good sell it.
