Edge Detection From Point Cloud Of Worn Parts

Nguyen, Keith Wei Liang; Aprilia, Aisyah Sabrina; Khairyanto, Ahmad; Pang, Wee Ching; Seet, Gerald; Tor, Shu Beng

doi:10.25341/d45c7s

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A standard approach is to compute at each point a geometric descriptor using the eigenstructure of the covariance matrix [Gumhold et al 2001]. It can be a ratio between the eigenvalues, taking into account their evaluation at different scales [Pauly et al 2003] or not [Xia and Wang 2017], or directly a curvature estimation [Lin et al 2015;Nguyen et al 2018]. The ratio between eigenvalues is considered as a more reliable parameter and it is, for instance, used in the CGAL Library [Alliez et al 2021] with a Delaunay-based feature estimation [Mérigot et al 2011].…”

Section: Edge Detectionmentioning

confidence: 99%

PCEDNet: A Lightweight Neural Network for Fast and Interactive Edge Detection in 3D Point Clouds

et al. 2021

View full text Add to dashboard Cite

In recent years, Convolutional Neural Networks (CNN) have proven to be efficient analysis tools for processing point clouds, e.g., for reconstruction, segmentation, and classification. In this article, we focus on the classification of edges in point clouds, where both edges and their surrounding are described. We propose a new parameterization adding to each point a set of differential information on its surrounding shape reconstructed at different scales. These parameters, stored in a Scale-Space Matrix (SSM) , provide a well-suited information from which an adequate neural network can learn the description of edges and use it to efficiently detect them in acquired point clouds. After successfully applying a multi-scale CNN on SSMs for the efficient classification of edges and their neighborhood, we propose a new lightweight neural network architecture outperforming the CNN in learning time, processing time, and classification capabilities. Our architecture is compact, requires small learning sets, is very fast to train, and classifies millions of points in seconds.

show abstract