A Novel Multi-view Three-dimensional Visual Measurement Method Based On Hexahedron Targets

Abstract

In order to meet the demand of coded light multi-view 3D reconstruction, we propose a highly efficient and accurate technique for point cloud registration, which can acquire the whole surface information of the measured piece without the help of other locating equipment. Method: First of all, we illustrate the principle of the hexahedron targets registration, establish the index point couples and present the registration patterns for each side of the target, as well as the recognition approach. Then, based on the quaternion preliminary registration, we propose an accurate registration method which combines the orthogonal Grey code and ICP. The result of the simulated experiment shows that the registration error of the hexahedron targets method is approximately 0.03mm, and during the actual experiment, the number is approximately 0.8mm, which is close to the global camera method and a little bit higher than the surface method. The new technique solves the problem that the measured surface cannot be placed with index points. Furthermore, this technique ensures the registration accuracy without any other apparatus.