Calculating distance with downward-tilted Vision Sensor?

Our team recently received a vision sensor, and we’re very excited about it!
My question is in the title: how do you use a downward-tilted vision sensor to determine the distance from an object?
The description blurb states:

My current theory is that the Y value of an object returned by the vision sensor is proportional to the FOV angle of the camera. This angle + the height of the Vision Sensor could then be used to determine distance. Is this the right line of thinking? If so, what would the pseudo-code look like practice?