I was testing an algorithm that returns me to the area of objects based on a reference, a priori this gave me results very close to the real, when the reference was the same height of the object measured, but I decided to observe at a different height, with that I verified that the given area was bigger than I expected.
Reference is the circle on the left and the object is on the right on the 11cm diameter pipe.
I figured it was due to the curvature of the tube, but as it turned out quite high I figured it was due to the proximity of the camera, and since I'm using a pixel count method this problem might have occurred.
I wonder if there is another way to get this area without being counted pixels or some way to reverse this difference?