This tutorial shows how to use the intrinsic camera calibration package to compute the camera intrinsic parameters using a rail guide and calibration target. The procedure uses a slightly different cost function than OpenCV and Matlab. It relies on knowing the distance the camera is moved between successive images. When performed precisely, the routine is both quicker because it requires fewer images and more accurate because the parameters have lower co-variance.

This tutorial explains how to perform an extrinsic calibration of a network of cameras, through two examples. You will learn how to write and run a calibration script which defines the cameras, the targets, and a series of observations. You will also learn how to modify an existing Xacro or Urdf model to provide a seamless interface for installing the calibration results. You will also be introduced to the concept of a cost function. One significant contribution of this library is the variety of cost functions it contains.

This tutorial shows how to perform the extrinsic calibration of a David SLS-2 3D sensor on an industrial Fanuc robot.

This tutorial will explain how to use the industrial_extrinsic_cal package to calibrate one or two cameras to a checkerboard or circle grid target. If using two cameras, they both should have the same target in their field of view. If using the unchanged repository provided yaml files for parameters, then you will need at least one Asus/Kinect cameras and a checkerboard (12x12 square checkerboard (11x11 points)) or circle grid (5x7 circles).

Simple example for industrial extrinsic calibration using a webcam