A study on local feature descriptors for point clouds
Autor(a) principal: | |
---|---|
Data de Publicação: | 2017 |
Tipo de documento: | Trabalho de conclusão de curso |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFRN |
Texto Completo: | https://repositorio.ufrn.br/handle/123456789/34187 |
Resumo: | Point clouds are a way of representing 3D data which became very popular due to the rise of low-cost 3D sensors on the market whose output data is represented as a point cloud. Given it low-cost, these sensors have been used used in many different fields, such as games or robotics. In many of these applications, recognizing patterns inside big, unorganized clouds is a fundamental task which is often solved using local feature descriptors, which are a way of encoding information local to a region inside a bigger cloud. Nevertheless, pattern recognition using local feature descriptors is a hard task, whose results nowadays are far from satisfactory (in terms of quality and speed) for most of the non-synthetic scenarios, which motivates the development of new descriptors. As a first series of experiments towards both fast descriptors and descriptors robust to high clutter and occlusion, we develop five descriptors, two of them being simplified (thus faster) versions of existing state-of-the-art techniques, one a totally novel approach to discrete descriptors and two being extensions and adaptations of existing descriptors. Our tests show that although our proposals perform poorly when compared to the state-of-the-art, their simplistic design is enough to achieve reasonable results and perform close to some existing techniques, motivating us to keep improving these results. As a byproduct of our work, we produced a benchmark platform which is open for public usage and improvement, aiming to encourage the standardization of tests with feature descriptors. |
id |
UFRN_bffa7dbd6d4c1b6168e6818098142ca2 |
---|---|
oai_identifier_str |
oai:https://repositorio.ufrn.br:123456789/34187 |
network_acronym_str |
UFRN |
network_name_str |
Repositório Institucional da UFRN |
repository_id_str |
|
spelling |
Rocha, Luís Cláudio GouveiaCarvalho, Bruno Motta deGomes, Rafael BeserraAngeles, Edgar GarduñoCarvalho, Bruno Motta de2017-12-15T12:48:57Z2021-09-20T11:46:43Z2017-12-15T12:48:57Z2021-09-20T11:46:43Z2017-11-242013042960ROCHA, Luís Cláudio Gouveia. A study on local feature descriptors for point clouds. 2017. 76 f. TCC (Graduação) - Curso de Ciência da Computação, Departamento de Informática e Matemática Aplicada, Universidade Federal do Rio Grande do Norte, Natal, 2017.https://repositorio.ufrn.br/handle/123456789/34187Universidade Federal do Rio Grande do NorteUFRNBrasilCiência da Computaçãopoints cloudslocal feature descriptorsCNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::METODOLOGIA E TECNICAS DA COMPUTACAO::PROCESSAMENTO GRAFICO (GRAPHICS)A study on local feature descriptors for point cloudsinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/bachelorThesisPoint clouds are a way of representing 3D data which became very popular due to the rise of low-cost 3D sensors on the market whose output data is represented as a point cloud. Given it low-cost, these sensors have been used used in many different fields, such as games or robotics. In many of these applications, recognizing patterns inside big, unorganized clouds is a fundamental task which is often solved using local feature descriptors, which are a way of encoding information local to a region inside a bigger cloud. Nevertheless, pattern recognition using local feature descriptors is a hard task, whose results nowadays are far from satisfactory (in terms of quality and speed) for most of the non-synthetic scenarios, which motivates the development of new descriptors. As a first series of experiments towards both fast descriptors and descriptors robust to high clutter and occlusion, we develop five descriptors, two of them being simplified (thus faster) versions of existing state-of-the-art techniques, one a totally novel approach to discrete descriptors and two being extensions and adaptations of existing descriptors. Our tests show that although our proposals perform poorly when compared to the state-of-the-art, their simplistic design is enough to achieve reasonable results and perform close to some existing techniques, motivating us to keep improving these results. As a byproduct of our work, we produced a benchmark platform which is open for public usage and improvement, aiming to encourage the standardization of tests with feature descriptors.info:eu-repo/semantics/openAccessengreponame:Repositório Institucional da UFRNinstname:Universidade Federal do Rio Grande do Norte (UFRN)instacron:UFRNTEXTPointClouds_Rocha_2017.pdf.txtExtracted texttext/plain108119https://repositorio.ufrn.br/bitstream/123456789/34187/1/PointClouds_Rocha_2017.pdf.txt9e20a91ccdd26d0bda4ac999fb9adb69MD51ORIGINALPointClouds_Rocha_2017.pdfMonografiaapplication/pdf3450868https://repositorio.ufrn.br/bitstream/123456789/34187/2/PointClouds_Rocha_2017.pdf0cbc7e1b42960e69f5c4cdbd1f6c95c8MD52CC-LICENSElicense_urlapplication/octet-stream49https://repositorio.ufrn.br/bitstream/123456789/34187/3/license_url924993ce0b3ba389f79f32a1b2735415MD53license_textapplication/octet-stream0https://repositorio.ufrn.br/bitstream/123456789/34187/4/license_textd41d8cd98f00b204e9800998ecf8427eMD54license_rdfapplication/octet-stream0https://repositorio.ufrn.br/bitstream/123456789/34187/5/license_rdfd41d8cd98f00b204e9800998ecf8427eMD55LICENSElicense.txttext/plain756https://repositorio.ufrn.br/bitstream/123456789/34187/6/license.txta80a9cda2756d355b388cc443c3d8a43MD56123456789/341872021-09-20 08:46:43.457oai:https://repositorio.ufrn.br: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ório de PublicaçõesPUBhttp://repositorio.ufrn.br/oai/opendoar:2021-09-20T11:46:43Repositório Institucional da UFRN - Universidade Federal do Rio Grande do Norte (UFRN)false |
dc.title.pr_BR.fl_str_mv |
A study on local feature descriptors for point clouds |
title |
A study on local feature descriptors for point clouds |
spellingShingle |
A study on local feature descriptors for point clouds Rocha, Luís Cláudio Gouveia points clouds local feature descriptors CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::METODOLOGIA E TECNICAS DA COMPUTACAO::PROCESSAMENTO GRAFICO (GRAPHICS) |
title_short |
A study on local feature descriptors for point clouds |
title_full |
A study on local feature descriptors for point clouds |
title_fullStr |
A study on local feature descriptors for point clouds |
title_full_unstemmed |
A study on local feature descriptors for point clouds |
title_sort |
A study on local feature descriptors for point clouds |
author |
Rocha, Luís Cláudio Gouveia |
author_facet |
Rocha, Luís Cláudio Gouveia |
author_role |
author |
dc.contributor.referees1.none.fl_str_mv |
Carvalho, Bruno Motta de |
dc.contributor.referees2.none.fl_str_mv |
Gomes, Rafael Beserra |
dc.contributor.referees3.none.fl_str_mv |
Angeles, Edgar Garduño |
dc.contributor.author.fl_str_mv |
Rocha, Luís Cláudio Gouveia |
dc.contributor.advisor1.fl_str_mv |
Carvalho, Bruno Motta de |
contributor_str_mv |
Carvalho, Bruno Motta de |
dc.subject.pr_BR.fl_str_mv |
points clouds local feature descriptors |
topic |
points clouds local feature descriptors CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::METODOLOGIA E TECNICAS DA COMPUTACAO::PROCESSAMENTO GRAFICO (GRAPHICS) |
dc.subject.cnpq.fl_str_mv |
CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::METODOLOGIA E TECNICAS DA COMPUTACAO::PROCESSAMENTO GRAFICO (GRAPHICS) |
description |
Point clouds are a way of representing 3D data which became very popular due to the rise of low-cost 3D sensors on the market whose output data is represented as a point cloud. Given it low-cost, these sensors have been used used in many different fields, such as games or robotics. In many of these applications, recognizing patterns inside big, unorganized clouds is a fundamental task which is often solved using local feature descriptors, which are a way of encoding information local to a region inside a bigger cloud. Nevertheless, pattern recognition using local feature descriptors is a hard task, whose results nowadays are far from satisfactory (in terms of quality and speed) for most of the non-synthetic scenarios, which motivates the development of new descriptors. As a first series of experiments towards both fast descriptors and descriptors robust to high clutter and occlusion, we develop five descriptors, two of them being simplified (thus faster) versions of existing state-of-the-art techniques, one a totally novel approach to discrete descriptors and two being extensions and adaptations of existing descriptors. Our tests show that although our proposals perform poorly when compared to the state-of-the-art, their simplistic design is enough to achieve reasonable results and perform close to some existing techniques, motivating us to keep improving these results. As a byproduct of our work, we produced a benchmark platform which is open for public usage and improvement, aiming to encourage the standardization of tests with feature descriptors. |
publishDate |
2017 |
dc.date.accessioned.fl_str_mv |
2017-12-15T12:48:57Z 2021-09-20T11:46:43Z |
dc.date.available.fl_str_mv |
2017-12-15T12:48:57Z 2021-09-20T11:46:43Z |
dc.date.issued.fl_str_mv |
2017-11-24 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/bachelorThesis |
format |
bachelorThesis |
status_str |
publishedVersion |
dc.identifier.pr_BR.fl_str_mv |
2013042960 |
dc.identifier.citation.fl_str_mv |
ROCHA, Luís Cláudio Gouveia. A study on local feature descriptors for point clouds. 2017. 76 f. TCC (Graduação) - Curso de Ciência da Computação, Departamento de Informática e Matemática Aplicada, Universidade Federal do Rio Grande do Norte, Natal, 2017. |
dc.identifier.uri.fl_str_mv |
https://repositorio.ufrn.br/handle/123456789/34187 |
identifier_str_mv |
2013042960 ROCHA, Luís Cláudio Gouveia. A study on local feature descriptors for point clouds. 2017. 76 f. TCC (Graduação) - Curso de Ciência da Computação, Departamento de Informática e Matemática Aplicada, Universidade Federal do Rio Grande do Norte, Natal, 2017. |
url |
https://repositorio.ufrn.br/handle/123456789/34187 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Universidade Federal do Rio Grande do Norte |
dc.publisher.initials.fl_str_mv |
UFRN |
dc.publisher.country.fl_str_mv |
Brasil |
dc.publisher.department.fl_str_mv |
Ciência da Computação |
publisher.none.fl_str_mv |
Universidade Federal do Rio Grande do Norte |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFRN instname:Universidade Federal do Rio Grande do Norte (UFRN) instacron:UFRN |
instname_str |
Universidade Federal do Rio Grande do Norte (UFRN) |
instacron_str |
UFRN |
institution |
UFRN |
reponame_str |
Repositório Institucional da UFRN |
collection |
Repositório Institucional da UFRN |
bitstream.url.fl_str_mv |
https://repositorio.ufrn.br/bitstream/123456789/34187/1/PointClouds_Rocha_2017.pdf.txt https://repositorio.ufrn.br/bitstream/123456789/34187/2/PointClouds_Rocha_2017.pdf https://repositorio.ufrn.br/bitstream/123456789/34187/3/license_url https://repositorio.ufrn.br/bitstream/123456789/34187/4/license_text https://repositorio.ufrn.br/bitstream/123456789/34187/5/license_rdf https://repositorio.ufrn.br/bitstream/123456789/34187/6/license.txt |
bitstream.checksum.fl_str_mv |
9e20a91ccdd26d0bda4ac999fb9adb69 0cbc7e1b42960e69f5c4cdbd1f6c95c8 924993ce0b3ba389f79f32a1b2735415 d41d8cd98f00b204e9800998ecf8427e d41d8cd98f00b204e9800998ecf8427e a80a9cda2756d355b388cc443c3d8a43 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFRN - Universidade Federal do Rio Grande do Norte (UFRN) |
repository.mail.fl_str_mv |
|
_version_ |
1802117759482462208 |