Detection of Closed Sharp Feature Lines in Point Clouds for Reverse Engineering Applications

Abstract

The reconstruction of a surface model from a point cloud is an important task in the reverse engineering of industrial parts. We aim at constructing a curve network on the point cloud that will define the border of the various surface patches. In this paper, we present an algorithm to extract closed sharp feature lines, which is necessary to create such a closed curve network. We use a first order segmentation to extract candidate feature points and process them as a graph to recover the sharp feature lines. To this end, a minimum spanning tree is constructed and afterwards a reconnection procedure closes the lines. The algorithm is fast and gives good results for real-world point sets from industrial applications.

Curvature-direction measures for 3D feature detection

“…Novel corner and edge detectors are then derived using these partial derivatives. Demarsin et al [11] used PCA (principal component analysis) to calculate the normal direction of points, and feature point is extracted through the changed size of adjacent points. Lai et al [12] presented the idea of integral invariants, and proposed a robust feature extraction and classification algorithm.…”

Robust Smooth Feature Extraction from Point Clouds

“…Both techniques [9,16] connect the flagged points using a minimum spanning tree and fit curves to approximate sharp edges. Demarsin et al [5] compute point normals using principal component analysis and segment the points into groups based on the normal variation in local neighborhoods. A minimum spanning tree is constructed between the boundary points of the assorted clusters, which is used to build the final feature curves.…”

A Novel Self-Positioning Based on Feature Map Creation and Laser Location Method for RBPF-SLAM

“…e speed of feature map recognition determines the efficiency of unmanned vehicle positioning and map construction, which is the core problem of unmanned vehicle navigation and the basis of solving the movement control of unmanned vehicle. Currently, the widely used linear segment segmentation and extraction algorithms of laser scanning data include S&M (Split-and-Merge) algorithm, RANSAC (Random Sample Consensus) algorithm, LR (Line Regression) algorithm, IEPF (Iterative Endpoint Fit) algorithm, and EM (Expectation Maximization) algorithm, all of which are compared in detail in literature [1]. IEPF algorithm based on Hough transform is a common and efficient recursive algorithm to extract the point set of laser SLAM into line segment features.…”