Raycasting-Based Stereo-to-CAD Registration for Industrial Inspection

Abstract

Image-based industrial inspection enables fast detection of cracks, dents, and coating defects but often lacks metric quantification, while 3-D methods typically involve greater acquisition complexity and challenging automation. When accurate computer-aided design models are available, quantitative inspection can instead be conducted as high-precision image-to-model registration under imperfect initialization and geometric deviations. This study introduces a raycasting-based iterative registration method that maps stereo image keypoints to a reference mesh and refines pose via triangulation and iterative closest point algorithm. To emulate positioning uncertainty, the measurement object is mounted on a three-axis linear stage and translated from its nominal pose. Results show sub-0.2 mm translation accuracy for initial offsets up to 2.5 mm. A sequential procedure with additional coarse alignment extends the convergence range to 8 mm. Conventional registration exhibits systematic residual error along the dominant geometric sliding axis, which is reduced by the proposed refinement strategy.