A Novel Approach to Calibrate a Structured Light Vision Sensor in a Robot Based 3D Measurement System

摘要

A robot based 3D measurement system Is presentedto overcome the disadvantages of coordinate measuring machine(CMM). As to calibrate the vision sensor in the system, a novelprocedure that utilizes the robot to generate sufficient calibrationpoints with high accuracy is proposed. The approach is based on anumber of fixed points printed in a paper which is of low-cost. Amultilayer perceptron neural network (MLPNN) approach tocalibrate the vision sensor is proposed. Various trainingalgorithms for MLPNN are tested and the best performance one isemployed to train the designed MLPNN. Using a standard part tovalidate the effectiveness of the presented technique, experimentalresults demonstrate designed MLPNN can achieve an accuratemodel for the structured light vision sensor.