Most cameras, especially wide angular ones, exhibit a large distortion. We can model such distortion as radial or tangential and compute the coefficients of that model using calibration algorithms. The camera calibration algorithms also allow us to obtain a calibration matrix that contains the focal distance and principal point of the lens, and hence provides a way to measure distances in meters in the world using the images acquired. In the case of stereo vision, it is also possible to retrieve depth information, that is, the distance of the pixels to the camera, as we will see later. Consequently, we will have 3D information of the world.
The calibration is done by showing several views of a known image named calibration pattern, which is typically a chessboard. It can also be an array of circles, or an asymmetric pattern of circles. Note that circles are seen as ellipses by the cameras for skew views. A detection algorithm obtains the inner corner point of the...