1. PCEDNet: A Lightweight Neural Network for Fast and Interactive Edge Detection in 3D Point Clouds
- Author
-
HimeurChems-Eddine, PellegriniThomas, BartheLoic, MelladoNicolas, LejembleThibault, PaulinMathias, Structural Models and Tools in Computer Graphics (IRIT-STORM), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Équipe Structuration, Analyse et MOdélisation de documents Vidéo et Audio (IRIT-SAMoVA), and ANR-11-BS02-0006,ALTA,Analyse des opérateurs de transport lumineux et applications(2011)
- Subjects
low resource computing ,FOS: Computer and information sciences ,Computer science ,Point cloud ,02 engineering and technology ,Convolutional neural network ,Edge detection ,Computer Science - Graphics ,0202 electrical engineering, electronic engineering, information engineering ,Segmentation ,energy efficiency ,edge detection ,Artificial neural network ,business.industry ,datasets ,[INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM] ,020207 software engineering ,Pattern recognition ,neural networks ,Computer Graphics and Computer-Aided Design ,[INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR] ,Graphics (cs.GR) ,020201 artificial intelligence & image processing ,Artificial intelligence ,Analysis tools ,business ,Efficient energy use - Abstract
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.
- Published
- 2021
- Full Text
- View/download PDF