Recognising geometric primitives in 3D point clouds of mechanical CAD objects

Abstract

The problem faced in this paper concerns the recognition of simple and complex geometric primitives in point clouds resulting from scans of mechanical CAD objects. A large number of points, the presence of noise, outliers, missing or redundant parts and uneven distribution are the main problems to be addressed to meet this need. In this article we propose a solution, based on the Hough transform, that can recognize simple and complex geometric primitives and is robust to noise, outliers, and missing parts. Additionally, we can extract a series of geometric descriptors that uniquely characterize a primitive and, based on them, aggregate the output into maximal or compound primitives, thus reducing oversegmentation. The results presented in the paper demonstrate the robustness of the method and its competitiveness with respect to other solutions proposed in the literature.

References in corpus (4)

• Supervised Fitting of Geometric Primitives to 3D Point Clouds
• Fit4CAD: A point cloud benchmark for fitting simple geometric primitives in CAD objects
• Fitting and recognition of geometric primitives in segmented 3D point clouds using a localized voting procedure
• SHREC 2022: Fitting and recognition of simple geometric primitives on point clouds