Point2Wave: 3-D Point Cloud to Waveform Translation Using a Conditional Generative Adversarial Network With Dual Discriminators

Since 2017, many deep learning methods for 3-D point clouds observed by airborne LiDAR (airborne 3-D point clouds) have been proposed. Moreover, not only a deep learning method for airborne 3-D point clouds but also a deep learning method for points and their waveforms observed by full-waveform LiDA...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Takayuki Shinohara, Haoyi Xiu, Masashi Matsuoka
Formato: article
Lenguaje:EN
Publicado: IEEE 2021
Materias:
Acceso en línea:https://doaj.org/article/96f93527a30b4b37b508e9bbb88b7271
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:96f93527a30b4b37b508e9bbb88b7271
record_format dspace
spelling oai:doaj.org-article:96f93527a30b4b37b508e9bbb88b72712021-11-25T00:00:13ZPoint2Wave: 3-D Point Cloud to Waveform Translation Using a Conditional Generative Adversarial Network With Dual Discriminators2151-153510.1109/JSTARS.2021.3124610https://doaj.org/article/96f93527a30b4b37b508e9bbb88b72712021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9599498/https://doaj.org/toc/2151-1535Since 2017, many deep learning methods for 3-D point clouds observed by airborne LiDAR (airborne 3-D point clouds) have been proposed. Moreover, not only a deep learning method for airborne 3-D point clouds but also a deep learning method for points and their waveforms observed by full-waveform LiDAR (airborne FW data) was proposed. We need to achieve highly accurate land cover classification by using airborne FW data, but open data often only have airborne 3-D point clouds available. Therefore, to improve the performance of land cover classification when using airborne 3-D point clouds published as open data, it is important to restore waveforms from airborne 3-D point clouds. In this article, we propose a deep learning model to translate an airborne 3-D point cloud to airborne FW data (called a point-to-waveform translation model, point2wave) using a conditional generative adversarial net (cGAN). Our point2wave is a cGAN pipeline consisting of a generator that translates the waveform corresponding to each point from the input airborne 3-D point cloud and discriminators that calculate the distance between the translated waveform and the ground truth waveform. Using a set of point clouds and waveforms dataset, we have experimented to translate points into the waveforms by point2wave. Experimental results showed that point2wave could translate waveforms from the airborne 3-D point cloud and the translated fake waveforms achieved nearly the same land cover classification performance as the real waveforms.Takayuki ShinoharaHaoyi XiuMasashi MatsuokaIEEEarticleAirborne LiDARconditional generative adversarial networkdeep learningfull waveform LiDAROcean engineeringTC1501-1800Geophysics. Cosmic physicsQC801-809ENIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 11630-11642 (2021)
institution DOAJ
collection DOAJ
language EN
topic Airborne LiDAR
conditional generative adversarial network
deep learning
full waveform LiDAR
Ocean engineering
TC1501-1800
Geophysics. Cosmic physics
QC801-809
spellingShingle Airborne LiDAR
conditional generative adversarial network
deep learning
full waveform LiDAR
Ocean engineering
TC1501-1800
Geophysics. Cosmic physics
QC801-809
Takayuki Shinohara
Haoyi Xiu
Masashi Matsuoka
Point2Wave: 3-D Point Cloud to Waveform Translation Using a Conditional Generative Adversarial Network With Dual Discriminators
description Since 2017, many deep learning methods for 3-D point clouds observed by airborne LiDAR (airborne 3-D point clouds) have been proposed. Moreover, not only a deep learning method for airborne 3-D point clouds but also a deep learning method for points and their waveforms observed by full-waveform LiDAR (airborne FW data) was proposed. We need to achieve highly accurate land cover classification by using airborne FW data, but open data often only have airborne 3-D point clouds available. Therefore, to improve the performance of land cover classification when using airborne 3-D point clouds published as open data, it is important to restore waveforms from airborne 3-D point clouds. In this article, we propose a deep learning model to translate an airborne 3-D point cloud to airborne FW data (called a point-to-waveform translation model, point2wave) using a conditional generative adversarial net (cGAN). Our point2wave is a cGAN pipeline consisting of a generator that translates the waveform corresponding to each point from the input airborne 3-D point cloud and discriminators that calculate the distance between the translated waveform and the ground truth waveform. Using a set of point clouds and waveforms dataset, we have experimented to translate points into the waveforms by point2wave. Experimental results showed that point2wave could translate waveforms from the airborne 3-D point cloud and the translated fake waveforms achieved nearly the same land cover classification performance as the real waveforms.
format article
author Takayuki Shinohara
Haoyi Xiu
Masashi Matsuoka
author_facet Takayuki Shinohara
Haoyi Xiu
Masashi Matsuoka
author_sort Takayuki Shinohara
title Point2Wave: 3-D Point Cloud to Waveform Translation Using a Conditional Generative Adversarial Network With Dual Discriminators
title_short Point2Wave: 3-D Point Cloud to Waveform Translation Using a Conditional Generative Adversarial Network With Dual Discriminators
title_full Point2Wave: 3-D Point Cloud to Waveform Translation Using a Conditional Generative Adversarial Network With Dual Discriminators
title_fullStr Point2Wave: 3-D Point Cloud to Waveform Translation Using a Conditional Generative Adversarial Network With Dual Discriminators
title_full_unstemmed Point2Wave: 3-D Point Cloud to Waveform Translation Using a Conditional Generative Adversarial Network With Dual Discriminators
title_sort point2wave: 3-d point cloud to waveform translation using a conditional generative adversarial network with dual discriminators
publisher IEEE
publishDate 2021
url https://doaj.org/article/96f93527a30b4b37b508e9bbb88b7271
work_keys_str_mv AT takayukishinohara point2wave3dpointcloudtowaveformtranslationusingaconditionalgenerativeadversarialnetworkwithdualdiscriminators
AT haoyixiu point2wave3dpointcloudtowaveformtranslationusingaconditionalgenerativeadversarialnetworkwithdualdiscriminators
AT masashimatsuoka point2wave3dpointcloudtowaveformtranslationusingaconditionalgenerativeadversarialnetworkwithdualdiscriminators
_version_ 1718414708462059520