The “Artificial Vision” permits industrial automation and system vision able to act in the production activities without humane presence. So we suppose that the acquisition and interpretation of the imagines for automation purposes is an interesting topic. Industrial application are referred to technological fields (assembly or dismounting, cut or stock removal; electrochemical processes; abrasive trials; cold or warm moulding; design with CAD techniques; metrology), or about several processes (control of the row material; workmanship of the component; assemblage; packing or storages; controls of quality; maintenance). The main advantages of this technique are: 1) elimination of the human errors, particularly in the case of repetitive or monotonous operations; 2) possibility to vary the production acting on the power of the automatic system (the automatic machines can operate to high rhythms day and night every day of the year); 3) greater informative control through the acquisition of historical data; these data can be used for successive elaborations, for the analysis of the failures and to have statistics in real time; 4) quality control founded on objective parameters in order to avoid dispute, and loss of image. In addition, another interesting application can be considered: the robot cinematic calibration and the trajectories recording. First of all it is important to consider that, by a suitable cameras calibration technique, it is possible to record three dimensional objects and trajectories by means of a couple of television cameras. By means of perspective transformation it is possible to associate a point in the geometric space to a point in a plane. In homomogeneous coordinates the perspective transformation matrix has non-zero elements in the fourth row.