From accurate range imaging sensor calibration to accurate model-based 3D object localization

The registration of multiple 3D data sets obtained with a laser range finder is examined. A sensor calibration technique based on the conjunction of a mathematical camera model, the N-planes B-spline (NPBS), with an accurate mechanical calibration setup, is proposed. An algorithm for recovering the rigid transformation (rotation and translation) between the two sets of 3D coordinates obtained by the calibrated imaging range sensor is developed. Its input is sets of points lying on the surface of the object. This input is converted into an octree-spline that allows point-to-surface distances to be computed quickly. A robust nonlinear least-squares minimization technique then finds the optimal pose by minimizing the sum of square distances between the two sets of 3D coordinates. The algorithm has been applied to matching human faces with highly accurate results.<<ETX>>