A novel 3D surface modeling based on Spatial Neighbor Points Coupling in reverse engineering

A novel 3D surface modeling method - 3D Surface Modeling based on Spatial Neighbor Points Coupling (SMSNPC) for scattered data points is addressed in this article. The main contribution contains two aspects: First, the 3D model of complex surface can be reconstructed through SMSNPC. Then, model parameters are recognized with Artificial Neural Network (ANN). To demonstrate the efficient applicability of the new algorithm, two groups of point data are presented. One collected by handheld laser scanner is used to validate the reconstruction result, and the other is used to be compared with non-coupling modeling. From the results, the new approach validates the expectation that SMSNPC can match the real complex surface satisfactorily which can´t be finished by non-coupling modeling. By comparing the same sample data with non-coupling modeling, it is shown the reconstruction precision of SMSNPC is much higher.