GPUMLib: Deep Learning SOM Library for Surface Reconstruction
Autor(a) principal: | |
---|---|
Data de Publicação: | 2017 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10314/3950 |
Resumo: | The evolution of 3D scanning devices and innovation in computer processing power and storage capacity has sparked the revolution of producing big point-cloud datasets. This phenomenon has becoming an integral part of the sophisticated building design process especially in the era of 4th Industrial Revolution. The big point-cloud datasets have caused complexity in handling surface reconstruction and visualization since existing algorithms are not so readily available. In this context, the surface reconstruction intelligent algorithms need to be revolutionized to deal with big point-cloud datasets in tandem with the advancement of hardware processing power and storage capacity. In this study, we propose GPUMLib – deep learning library for self-organizing map (SOM-DLLib) to solve problems involving big point-cloud datasets from 3D scanning devices. The SOM-DLLib consists of multiple layers for reducing and optimizing those big point cloud datasets. The findings show the final objects are successfully reconstructed with optimized neighborhood representation and the performance becomes better as the size of point clouds increases. |
id |
RCAP_1f8b2368d25e6df0721e812a8fcca2be |
---|---|
oai_identifier_str |
oai:bdigital.ipg.pt:10314/3950 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
GPUMLib: Deep Learning SOM Library for Surface ReconstructionSurface reconstruction, self-organizing map, deep learning, parallel computing, point cloudsThe evolution of 3D scanning devices and innovation in computer processing power and storage capacity has sparked the revolution of producing big point-cloud datasets. This phenomenon has becoming an integral part of the sophisticated building design process especially in the era of 4th Industrial Revolution. The big point-cloud datasets have caused complexity in handling surface reconstruction and visualization since existing algorithms are not so readily available. In this context, the surface reconstruction intelligent algorithms need to be revolutionized to deal with big point-cloud datasets in tandem with the advancement of hardware processing power and storage capacity. In this study, we propose GPUMLib – deep learning library for self-organizing map (SOM-DLLib) to solve problems involving big point-cloud datasets from 3D scanning devices. The SOM-DLLib consists of multiple layers for reducing and optimizing those big point cloud datasets. The findings show the final objects are successfully reconstructed with optimized neighborhood representation and the performance becomes better as the size of point clouds increases.Internacional Journal of Advances in Soft Computing and its Application2018-03-26T16:13:37Z2018-03-262017-07-30T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://hdl.handle.net/10314/3950http://hdl.handle.net/10314/3950eng2074-8523Lee, WaiHasan, ShafaatunnurShamsuddin, SitiLopes, Noelinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-01-14T02:57:42Zoai:bdigital.ipg.pt:10314/3950Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T01:43:07.659553Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
GPUMLib: Deep Learning SOM Library for Surface Reconstruction |
title |
GPUMLib: Deep Learning SOM Library for Surface Reconstruction |
spellingShingle |
GPUMLib: Deep Learning SOM Library for Surface Reconstruction Lee, Wai Surface reconstruction, self-organizing map, deep learning, parallel computing, point clouds |
title_short |
GPUMLib: Deep Learning SOM Library for Surface Reconstruction |
title_full |
GPUMLib: Deep Learning SOM Library for Surface Reconstruction |
title_fullStr |
GPUMLib: Deep Learning SOM Library for Surface Reconstruction |
title_full_unstemmed |
GPUMLib: Deep Learning SOM Library for Surface Reconstruction |
title_sort |
GPUMLib: Deep Learning SOM Library for Surface Reconstruction |
author |
Lee, Wai |
author_facet |
Lee, Wai Hasan, Shafaatunnur Shamsuddin, Siti Lopes, Noel |
author_role |
author |
author2 |
Hasan, Shafaatunnur Shamsuddin, Siti Lopes, Noel |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Lee, Wai Hasan, Shafaatunnur Shamsuddin, Siti Lopes, Noel |
dc.subject.por.fl_str_mv |
Surface reconstruction, self-organizing map, deep learning, parallel computing, point clouds |
topic |
Surface reconstruction, self-organizing map, deep learning, parallel computing, point clouds |
description |
The evolution of 3D scanning devices and innovation in computer processing power and storage capacity has sparked the revolution of producing big point-cloud datasets. This phenomenon has becoming an integral part of the sophisticated building design process especially in the era of 4th Industrial Revolution. The big point-cloud datasets have caused complexity in handling surface reconstruction and visualization since existing algorithms are not so readily available. In this context, the surface reconstruction intelligent algorithms need to be revolutionized to deal with big point-cloud datasets in tandem with the advancement of hardware processing power and storage capacity. In this study, we propose GPUMLib – deep learning library for self-organizing map (SOM-DLLib) to solve problems involving big point-cloud datasets from 3D scanning devices. The SOM-DLLib consists of multiple layers for reducing and optimizing those big point cloud datasets. The findings show the final objects are successfully reconstructed with optimized neighborhood representation and the performance becomes better as the size of point clouds increases. |
publishDate |
2017 |
dc.date.none.fl_str_mv |
2017-07-30T00:00:00Z 2018-03-26T16:13:37Z 2018-03-26 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10314/3950 http://hdl.handle.net/10314/3950 |
url |
http://hdl.handle.net/10314/3950 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
2074-8523 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Internacional Journal of Advances in Soft Computing and its Application |
publisher.none.fl_str_mv |
Internacional Journal of Advances in Soft Computing and its Application |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799136924223406080 |