Algorithm for Extracting Sharp Features from Point Cloud Models

Abstract:

Based on the moving least squares method, a method for extracting feature curves from point clouds was presented. Firstly the algorithm calculated projection residuals and potential feature points were identified in point cloud model. The potential feature points were then smoothed by employing a modified version of the principal component analysis approach. Subsequently, a feature-polyline propagation technique was used to approximate the feature points by a set of polylines. Finally the feature curves were optimized by the algorithm to resolve gaps and recover the junctions. Experiments show that the algorithm is very robust, and it can extract feature curves from various point clouds.