Loading...
Loading...

Go to the content (press return)

Correspondence matching in unorganized 3D point clouds using Convolutional Neural Networks

Author
Pujol, A.; Casas, J.; Ruiz-Hidalgo, J.
Type of activity
Journal article
Journal
Image and vision computing
Date of publication
2019-03-08
Volume
83-84
Number
March–April 2019
First page
51
Last page
60
DOI
10.1016/j.imavis.2019.02.013
Project funding
Multimodal Signal Processing and Machine Learning on Graphs
Repository
http://hdl.handle.net/2117/132169 Open in new window
URL
https://www.sciencedirect.com/science/article/pii/S0262885619300228 Open in new window
Abstract
This document presents a novel method based in Convolutional Neural Networks (CNN) to obtain correspondence matchings between sets of keypoints of several unorganized 3D point cloud captures, independently of the sensor used. The proposed technique extends a state-of-the-art method for correspondence matching in standard 2D images to sets of unorganized 3D point clouds. The strategy consists in projecting the 3D neighborhood of the keypoint onto an RGBD patch, and the classi cation of patch pair...
Citation
Pujol, A.; Casas, J.; Ruiz-Hidalgo, J. Correspondence matching in unorganized 3D point clouds using Convolutional Neural Networks. "Image and vision computing", 8 Març 2019, vol. 83-84, núm. March–April 2019, p. 51-60.
Keywords
convolutional neural networks, matching, point cloud
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants