Light field image quality enhancement by a lightweight deformable deep learning framework for intelligent transportation systems
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFLA |
Texto Completo: | http://repositorio.ufla.br/jspui/handle/1/49827 |
Resumo: | Light field (LF) imaging has multi-view properties that help to create many applications that include auto-refocusing, depth estimation and 3D reconstruction of images, which are required particularly for intelligent transportation systems (ITSs). However, cameras can present a limited angular resolution, becoming a bottleneck in vision applications. Thus, there is a challenge to incorporate angular data due to disparities in the LF images. In recent years, different machine learning algorithms have been applied to both image processing and ITS research areas for different purposes. In this work, a Lightweight Deformable Deep Learning Framework is implemented, in which the problem of disparity into LF images is treated. To this end, an angular alignment module and a soft activation function into the Convolutional Neural Network (CNN) are implemented. For performance assessment, the proposed solution is compared with recent state-of-the-art methods using different LF datasets, each one with specific characteristics. Experimental results demonstrated that the proposed solution achieved a better performance than the other methods. The image quality results obtained outperform state-of-the-art LF image reconstruction methods. Furthermore, our model presents a lower computational complexity, decreasing the execution time. |
id |
UFLA_62115ca4c05c4d6cccfdeccf9f0863d7 |
---|---|
oai_identifier_str |
oai:localhost:1/49827 |
network_acronym_str |
UFLA |
network_name_str |
Repositório Institucional da UFLA |
repository_id_str |
|
spelling |
Light field image quality enhancement by a lightweight deformable deep learning framework for intelligent transportation systemsLight field imagingDeep learning frameworkImage qualityComputational complexityIntelligent transportation systemsAprendizado profundoImagem - QualidadeComplexidade computacionalSistemas de Transporte InteligenteLight field (LF) imaging has multi-view properties that help to create many applications that include auto-refocusing, depth estimation and 3D reconstruction of images, which are required particularly for intelligent transportation systems (ITSs). However, cameras can present a limited angular resolution, becoming a bottleneck in vision applications. Thus, there is a challenge to incorporate angular data due to disparities in the LF images. In recent years, different machine learning algorithms have been applied to both image processing and ITS research areas for different purposes. In this work, a Lightweight Deformable Deep Learning Framework is implemented, in which the problem of disparity into LF images is treated. To this end, an angular alignment module and a soft activation function into the Convolutional Neural Network (CNN) are implemented. For performance assessment, the proposed solution is compared with recent state-of-the-art methods using different LF datasets, each one with specific characteristics. Experimental results demonstrated that the proposed solution achieved a better performance than the other methods. The image quality results obtained outperform state-of-the-art LF image reconstruction methods. Furthermore, our model presents a lower computational complexity, decreasing the execution time.Multidisciplinary Digital Publishing Institute (MDPI)2022-04-28T22:08:58Z2022-04-28T22:08:58Z2021-05info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfRIBEIRO, D. A. et al. Light field image quality enhancement by a lightweight deformable deep learning framework for intelligent transportation systems. Electronics, [S.I.], v. 10, n. 10, 2021. DOI: 10.3390/electronics10101136 .http://repositorio.ufla.br/jspui/handle/1/49827Electronicsreponame:Repositório Institucional da UFLAinstname:Universidade Federal de Lavras (UFLA)instacron:UFLAhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessRibeiro, David AugustoSilva, Juan CasavílcaRosa, Renata LopesSaadi, MuhammadMumtaz, ShahidWuttisittikulkij, LunchakornRodríguez, Demóstenes ZegarraOtaibi, Sattam Aleng2022-04-28T22:09:31Zoai:localhost:1/49827Repositório InstitucionalPUBhttp://repositorio.ufla.br/oai/requestnivaldo@ufla.br || repositorio.biblioteca@ufla.bropendoar:2022-04-28T22:09:31Repositório Institucional da UFLA - Universidade Federal de Lavras (UFLA)false |
dc.title.none.fl_str_mv |
Light field image quality enhancement by a lightweight deformable deep learning framework for intelligent transportation systems |
title |
Light field image quality enhancement by a lightweight deformable deep learning framework for intelligent transportation systems |
spellingShingle |
Light field image quality enhancement by a lightweight deformable deep learning framework for intelligent transportation systems Ribeiro, David Augusto Light field imaging Deep learning framework Image quality Computational complexity Intelligent transportation systems Aprendizado profundo Imagem - Qualidade Complexidade computacional Sistemas de Transporte Inteligente |
title_short |
Light field image quality enhancement by a lightweight deformable deep learning framework for intelligent transportation systems |
title_full |
Light field image quality enhancement by a lightweight deformable deep learning framework for intelligent transportation systems |
title_fullStr |
Light field image quality enhancement by a lightweight deformable deep learning framework for intelligent transportation systems |
title_full_unstemmed |
Light field image quality enhancement by a lightweight deformable deep learning framework for intelligent transportation systems |
title_sort |
Light field image quality enhancement by a lightweight deformable deep learning framework for intelligent transportation systems |
author |
Ribeiro, David Augusto |
author_facet |
Ribeiro, David Augusto Silva, Juan Casavílca Rosa, Renata Lopes Saadi, Muhammad Mumtaz, Shahid Wuttisittikulkij, Lunchakorn Rodríguez, Demóstenes Zegarra Otaibi, Sattam Al |
author_role |
author |
author2 |
Silva, Juan Casavílca Rosa, Renata Lopes Saadi, Muhammad Mumtaz, Shahid Wuttisittikulkij, Lunchakorn Rodríguez, Demóstenes Zegarra Otaibi, Sattam Al |
author2_role |
author author author author author author author |
dc.contributor.author.fl_str_mv |
Ribeiro, David Augusto Silva, Juan Casavílca Rosa, Renata Lopes Saadi, Muhammad Mumtaz, Shahid Wuttisittikulkij, Lunchakorn Rodríguez, Demóstenes Zegarra Otaibi, Sattam Al |
dc.subject.por.fl_str_mv |
Light field imaging Deep learning framework Image quality Computational complexity Intelligent transportation systems Aprendizado profundo Imagem - Qualidade Complexidade computacional Sistemas de Transporte Inteligente |
topic |
Light field imaging Deep learning framework Image quality Computational complexity Intelligent transportation systems Aprendizado profundo Imagem - Qualidade Complexidade computacional Sistemas de Transporte Inteligente |
description |
Light field (LF) imaging has multi-view properties that help to create many applications that include auto-refocusing, depth estimation and 3D reconstruction of images, which are required particularly for intelligent transportation systems (ITSs). However, cameras can present a limited angular resolution, becoming a bottleneck in vision applications. Thus, there is a challenge to incorporate angular data due to disparities in the LF images. In recent years, different machine learning algorithms have been applied to both image processing and ITS research areas for different purposes. In this work, a Lightweight Deformable Deep Learning Framework is implemented, in which the problem of disparity into LF images is treated. To this end, an angular alignment module and a soft activation function into the Convolutional Neural Network (CNN) are implemented. For performance assessment, the proposed solution is compared with recent state-of-the-art methods using different LF datasets, each one with specific characteristics. Experimental results demonstrated that the proposed solution achieved a better performance than the other methods. The image quality results obtained outperform state-of-the-art LF image reconstruction methods. Furthermore, our model presents a lower computational complexity, decreasing the execution time. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-05 2022-04-28T22:08:58Z 2022-04-28T22:08:58Z |
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 |
RIBEIRO, D. A. et al. Light field image quality enhancement by a lightweight deformable deep learning framework for intelligent transportation systems. Electronics, [S.I.], v. 10, n. 10, 2021. DOI: 10.3390/electronics10101136 . http://repositorio.ufla.br/jspui/handle/1/49827 |
identifier_str_mv |
RIBEIRO, D. A. et al. Light field image quality enhancement by a lightweight deformable deep learning framework for intelligent transportation systems. Electronics, [S.I.], v. 10, n. 10, 2021. DOI: 10.3390/electronics10101136 . |
url |
http://repositorio.ufla.br/jspui/handle/1/49827 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
http://creativecommons.org/licenses/by/4.0/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
http://creativecommons.org/licenses/by/4.0/ |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Multidisciplinary Digital Publishing Institute (MDPI) |
publisher.none.fl_str_mv |
Multidisciplinary Digital Publishing Institute (MDPI) |
dc.source.none.fl_str_mv |
Electronics reponame:Repositório Institucional da UFLA instname:Universidade Federal de Lavras (UFLA) instacron:UFLA |
instname_str |
Universidade Federal de Lavras (UFLA) |
instacron_str |
UFLA |
institution |
UFLA |
reponame_str |
Repositório Institucional da UFLA |
collection |
Repositório Institucional da UFLA |
repository.name.fl_str_mv |
Repositório Institucional da UFLA - Universidade Federal de Lavras (UFLA) |
repository.mail.fl_str_mv |
nivaldo@ufla.br || repositorio.biblioteca@ufla.br |
_version_ |
1784549976220631040 |