Cargando…

Airborne LiDAR point cloud classification using PointNet++ network with full neighborhood features

Compared with other point clouds, the airborne LiDAR point cloud has its own characteristics. The deep learning network PointNet++ ignores the inherent properties of airborne LiDAR point, and the classification precision is low. Therefore, we propose a framework based on the PointNet++ network. In t...

Descripción completa

Detalles Bibliográficos
Autores principales: Nong, Xingzhong, Bai, Wenfeng, Liu, Guanlan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9917240/
https://www.ncbi.nlm.nih.gov/pubmed/36763685
http://dx.doi.org/10.1371/journal.pone.0280346
_version_ 1784886323264356352
author Nong, Xingzhong
Bai, Wenfeng
Liu, Guanlan
author_facet Nong, Xingzhong
Bai, Wenfeng
Liu, Guanlan
author_sort Nong, Xingzhong
collection PubMed
description Compared with other point clouds, the airborne LiDAR point cloud has its own characteristics. The deep learning network PointNet++ ignores the inherent properties of airborne LiDAR point, and the classification precision is low. Therefore, we propose a framework based on the PointNet++ network. In this work, we proposed an interpolation method that uses adaptive elevation weight to make full use of the objects in the airborne LiDAR point, which exhibits discrepancies in elevation distributions. The class-balanced loss function is used for the uneven density distribution of point cloud data. Moreover, the relationship between a point and its neighbours is captured, densely connecting point pairs in multiscale regions and adding centroid features to learn contextual information. Experiments are conducted on the Vaihingen 3D semantic labelling benchmark dataset and GML(B) benchmark dataset. The experiments show that the proposed method, which has additional contextual information and makes full use of the airborne LiDAR point cloud properties to support classification, achieves high accuracy and can be widely used in airborne LiDAR point classification.
format Online
Article
Text
id pubmed-9917240
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-99172402023-02-11 Airborne LiDAR point cloud classification using PointNet++ network with full neighborhood features Nong, Xingzhong Bai, Wenfeng Liu, Guanlan PLoS One Research Article Compared with other point clouds, the airborne LiDAR point cloud has its own characteristics. The deep learning network PointNet++ ignores the inherent properties of airborne LiDAR point, and the classification precision is low. Therefore, we propose a framework based on the PointNet++ network. In this work, we proposed an interpolation method that uses adaptive elevation weight to make full use of the objects in the airborne LiDAR point, which exhibits discrepancies in elevation distributions. The class-balanced loss function is used for the uneven density distribution of point cloud data. Moreover, the relationship between a point and its neighbours is captured, densely connecting point pairs in multiscale regions and adding centroid features to learn contextual information. Experiments are conducted on the Vaihingen 3D semantic labelling benchmark dataset and GML(B) benchmark dataset. The experiments show that the proposed method, which has additional contextual information and makes full use of the airborne LiDAR point cloud properties to support classification, achieves high accuracy and can be widely used in airborne LiDAR point classification. Public Library of Science 2023-02-10 /pmc/articles/PMC9917240/ /pubmed/36763685 http://dx.doi.org/10.1371/journal.pone.0280346 Text en © 2023 Nong et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Nong, Xingzhong
Bai, Wenfeng
Liu, Guanlan
Airborne LiDAR point cloud classification using PointNet++ network with full neighborhood features
title Airborne LiDAR point cloud classification using PointNet++ network with full neighborhood features
title_full Airborne LiDAR point cloud classification using PointNet++ network with full neighborhood features
title_fullStr Airborne LiDAR point cloud classification using PointNet++ network with full neighborhood features
title_full_unstemmed Airborne LiDAR point cloud classification using PointNet++ network with full neighborhood features
title_short Airborne LiDAR point cloud classification using PointNet++ network with full neighborhood features
title_sort airborne lidar point cloud classification using pointnet++ network with full neighborhood features
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9917240/
https://www.ncbi.nlm.nih.gov/pubmed/36763685
http://dx.doi.org/10.1371/journal.pone.0280346
work_keys_str_mv AT nongxingzhong airbornelidarpointcloudclassificationusingpointnetnetworkwithfullneighborhoodfeatures
AT baiwenfeng airbornelidarpointcloudclassificationusingpointnetnetworkwithfullneighborhoodfeatures
AT liuguanlan airbornelidarpointcloudclassificationusingpointnetnetworkwithfullneighborhoodfeatures