On structured light vision sensor calibration in a robot based 3D laser scanning system

Abstract

A robot based 3D laser scanning system which a structured light vision sensor is mounted on the 6 degree-of-freedom robot is proposed to overcome the disadvantages of coordinate measuring machine (CMM). As to calibrate the vision sensor, a novel procedure that utilizes the robot to generate sufficient calibration points with high accuracy is proposed. An improved Tsai's method and a multilayer perceptron neural network (MLPNN) approach to calibrate the vision sensor are presented. The experimental performance comparisons are made between the above two approaches. Results demonstrate that both of the two presented methods can achieve an accurate model for the structured light vision sensor.