A multilevel feature-based method for mapping sparse point clouds to CAD models

Accurate mapping of sparse point clouds to CAD models is becoming increasingly crucial in fields such as digital twinning, 3D reconstruction, and engineering design. However, the sparsity and irregularity of point cloud data obtained through LiDAR scanning pose significant challenges to feature mapping precision and seamless integration with CAD models. Traditional methods struggle to maintain accurate mapping, especially when dealing with complex point cloud scenes or sparse data. These methods have significant limitations in accurately mapping sparse point clouds to solid models. To address these challenges, this paper introduces a multilevel feature mapping method that thoroughly analyzes the geometric features of both CAD models and point cloud data, significantly improving feature matching accuracy. In CAD model processing, the Geometric Feature Signature (GFS) mapping function is used to achieve high-precision geometric morphology descriptions through comprehensive extraction of geometric feature quantities. For point cloud data processing, Dense Domain Filtering (DDF) is employed to optimize the spatial distribution, minimizing the impact of noise and redundant data. Combined with Density-Controlled Geometric Consistent Feature Extraction (DC-GCFE), this method achieves accurate key feature point extraction from sparse point clouds by analyzing geometric feature quantities comprehensively. By efficiently matching the CAD model's geometric features with the point cloud's local and global features, the proposed multilevel feature mapping method ensures precise mapping even in sparse and complex point cloud environments, offering strong support for virtual simulation and design optimization. In comparison with traditional methods, this approach excels at capturing complex details and handling missing features. Finally, experimental validation confirms the method's high matching accuracy and robustness in complex scenes, verifying its effectiveness in precisely mapping sparse point clouds to CAD models.