A 3-D vision system model for automatic object surface sensing

Abstract

The development of a noncontact “light striping” (structured light) based three-dimensional, six-degrees-of-freedom vision system for automatic object surface sensing is reported. The system modeling and world-point reconstruction methodology involve homogeneous-coordinate system transformations applied in two independent stages: the video imaging stage using three-dimensional perspective transformations and the mechanical scanning stage using three-dimensional affine transformations. Concatenation of the two independent matrix models leads to a robust four-by-four, six-degrees-of-freedom system model. The reconstructed sectional contours are registered automatically in real time with respect to a common world-coordinate system as a control net for Non-Uniform Rational B-spline (NURBS) surface approximation. The reconstruction process is demonstrated by measuring the surface of a 19.5×2 ft rowing shell. A detailed statistical accuracy and precision analysis shows an average error of 0.2% (0.002) of the camera's field-of-view. System sensitivity analysis reveals a nonlinear increase of sensitivity for angles higher than 45° between the normals of the image and laser planes.