Fechar

1. Identificação
Tipo de ReferênciaArtigo em Evento (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Código do Detentoribi 8JMKD3MGPEW34M/46T9EHH
Identificador8JMKD3MGPEW34M/43BD4BE
Repositóriosid.inpe.br/sibgrapi/2020/09.30.00.38
Última Atualização2020:09.30.02.06.02 (UTC) administrator
Repositório de Metadadossid.inpe.br/sibgrapi/2020/09.30.00.38.53
Última Atualização dos Metadados2022:06.14.00.00.13 (UTC) administrator
DOI10.1109/SIBGRAPI51738.2020.00038
Chave de CitaçãoCerpaSalasMezaLoaiBarb:2020:TrSyIm
TítuloTraining with synthetic images for object detection and segmentation in real machinery images
FormatoOn-line
Ano2020
Data de Acesso17 maio 2024
Número de Arquivos1
Tamanho4696 KiB
2. Contextualização
Autor1 Cerpa Salas, Alonso Jesús
2 Meza Lovón, Graciela Lecireth
3 Loaiza Fernández, Manuel Eduardo
4 Barbosa Raposo, Alberto
Afiliação1 Universidad Católica San Pablo
2 Universidad Católica San Pablo
3 Universidad Católica San Pablo
4 Pontifical Catholic University of Rio de Janeiro
EditorMusse, Soraia Raupp
Cesar Junior, Roberto Marcondes
Pelechano, Nuria
Wang, Zhangyang (Atlas)
Endereço de e-Mailalonso.cerpa@ucsp.edu.pe
Nome do EventoConference on Graphics, Patterns and Images, 33 (SIBGRAPI)
Localização do EventoPorto de Galinhas (virtual)
Data7-10 Nov. 2020
Editora (Publisher)IEEE Computer Society
Cidade da EditoraLos Alamitos
Título do LivroProceedings
Tipo TerciárioFull Paper
Histórico (UTC)2020-09-30 02:06:04 :: alonso.cerpa@ucsp.edu.pe -> administrator :: 2020
2022-06-14 00:00:13 :: administrator -> alonso.cerpa@ucsp.edu.pe :: 2020
3. Conteúdo e estrutura
É a matriz ou uma cópia?é a matriz
Estágio do Conteúdoconcluido
Transferível1
Tipo de Versãofinaldraft
Palavras-Chavesynthetic data generation
object detection
object segmentation
deep learning
ResumoOver the last years, Convolutional Neural Networks have been extensively used for solving problems such as image classification, object segmentation, and object detection. However, deep neural networks require a great deal of data correctly labeled in order to perform properly. Generally, generation and labeling processes are carried out by recruiting people to label the data manually. To overcome this problem, many researchers have studied the use of data generated automatically by a renderer. To the best of our knowledge, most of this research was conducted for general-purpose domains but not for specific ones. This paper presents a methodology to generate synthetic data and train a deep learning model for the segmentation of pieces of machinery. For doing so, we built a computer graphics synthetic 3D scenery with the 3D models of real pieces of machinery for rendering and capturing virtual photos from this 3D scenery. Subsequently, we train a Mask R-CNN using the pre-trained weights of COCO dataset. Finally, we obtained our best averages of 85.7% mAP for object detection and 84.8% mAP for object segmentation, over our real test dataset and training only with synthetic images filtered with Gaussian Blur.
Arranjo 1urlib.net > SDLA > Fonds > SIBGRAPI 2020 > Training with synthetic...
Arranjo 2urlib.net > SDLA > Fonds > Full Index > Training with synthetic...
Conteúdo da Pasta docacessar
Conteúdo da Pasta source
paper_sibgrapi_id54.pdf 29/09/2020 21:38 4.6 MiB
PID6630889.pdf 29/09/2020 22:50 4.6 MiB
Conteúdo da Pasta agreement
agreement.html 29/09/2020 21:38 1.2 KiB 
4. Condições de acesso e uso
URL dos dadoshttp://urlib.net/ibi/8JMKD3MGPEW34M/43BD4BE
URL dos dados zipadoshttp://urlib.net/zip/8JMKD3MGPEW34M/43BD4BE
Idiomaen
Arquivo AlvoPID6630889.pdf
Grupo de Usuáriosalonso.cerpa@ucsp.edu.pe
Visibilidadeshown
Permissão de Atualizaçãonão transferida
5. Fontes relacionadas
Repositório Espelhosid.inpe.br/banon/2001/03.30.15.38.24
Unidades Imediatamente Superiores8JMKD3MGPEW34M/43G4L9S
8JMKD3MGPEW34M/4742MCS
Lista de Itens Citandosid.inpe.br/sibgrapi/2020/10.28.20.46 5
Acervo Hospedeirosid.inpe.br/banon/2001/03.30.15.38
6. Notas
Campos Vaziosarchivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination edition electronicmailaddress group isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url volume
7. Controle da descrição
e-Mail (login)alonso.cerpa@ucsp.edu.pe
atualizar 


Fechar