Calibration method for the HALCON based machine vision system

Abstract

At present, the commonly used calibration method in industry is "nine-point calibration method", which uses the attitude change of the manipulator to calibration the system through affine transformation, but the traditional calibration method is complicated and easy to be affected by lighting and other factors. To improve the calibration efficiency, and to reduce the calibration error, the paper proposes a calibration method for machine vision systems based on HALCON. Firstly, the camera is used to collect the image to obtain the parameters of the camera; secondly, the hand-eye calibration is used to obtain the attitude of the tool coordinate system of the end of the manipulator to the machine, and the experiment shows that the calibration method can improve the accuracy of the machine vision system and meet the requirements of industrial robots. The hardware of the visual system mainly includes 3D camera, industrial controller, controller and manipulator, using the HALCON machine vision algorithm package, with the characteristics of short period and high program stability.