Machine vision based control of the ball and beam

The use of vision systems in motion control applications puts hard real-time constrains on image processing. However, constantly increasing performances and decreasing prices of vision hardware make vision measuring systems concurrent to other measuring systems in these applications, where vision systems can be used to precisely measure number of variables such as length, angle, position, orientation, etc. The main advantage of a vision measuring system in these applications is its noncontact measurement principle, which is important in cases when it is difficult to implement contact measurements. Apart from real-time constraints, the biggest problem that limits the applications of a machine vision system is its robustness to the noise present in the image as well as to the scene disturbances caused by background and foreground objects and to the nonideal illumination conditions. A simple, computationally efficient and robust machine vision measuring system is described, which is suitable for real-time angle measurement. Its behavior is experimentally tested on a ball and beam benchmark process, where high quality measurement of the beam angle is achieved even in nonideal lighting condition and also when no white background is used. The implemented vision system is used for feedback control of the ball and beam.