SpaceYNet: A Novel Approach to Pose and Depth-Scene Regression Simultaneously

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniv Fed Paraiba-
Autor(es): dc.contributorUniversidade Estadual Paulista (Unesp)-
Autor(es): dc.creatorAragao, Dunfrey-
Autor(es): dc.creatorNascimento, Tiago-
Autor(es): dc.creatorMondini, Adriano [UNESP]-
Autor(es): dc.creatorPaiva, A. C.-
Autor(es): dc.creatorConci, A.-
Autor(es): dc.creatorBraz, G.-
Autor(es): dc.creatorAlmeida, JDS-
Autor(es): dc.creatorFernandes, LAF-
Data de aceite: dc.date.accessioned2022-02-22T00:55:38Z-
Data de disponibilização: dc.date.available2022-02-22T00:55:38Z-
Data de envio: dc.date.issued2021-06-25-
Data de envio: dc.date.issued2021-06-25-
Data de envio: dc.date.issued2019-12-31-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/209189-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/209189-
Descrição: dc.descriptionOne of the fundamental dilemmas of mobile robotics is the use of sensory information to locate an agent in geographic space. In this paper, we developed a global relocation system to predict the robot's position and avoid unforeseen actions from a monocular image, which we named SpaceYNet. We incorporated Inception layers to symmetric layers of down-sampling and upsampling to solve depth-scene and 6-DoF estimation simultaneously. Also, we compared SpaceYNet to PoseNet - a state of the art in robot pose regression using CNN - in order to evaluate it. The comparison comprised one public dataset and one created in a broad indoor environment. SpaceYNet showed higher accuracy in global percentages when compared to PoseNet.-
Descrição: dc.descriptionUniv Fed Paraiba, Joao Pessoa, Paraiba, Brazil-
Descrição: dc.descriptionUniv Estadual Paulista, Sao Paulo, Brazil-
Descrição: dc.descriptionUniv Estadual Paulista, Sao Paulo, Brazil-
Formato: dc.format217-222-
Idioma: dc.languageen-
Publicador: dc.publisherIeee-
Relação: dc.relationProceedings Of The 2020 International Conference On Systems, Signals And Image Processing (iwssip), 27th Edition-
???dc.source???: dc.sourceWeb of Science-
Palavras-chave: dc.subjectDataset-
Palavras-chave: dc.subjectdepth-scene-
Palavras-chave: dc.subjectpose-
Palavras-chave: dc.subjectregression-
Palavras-chave: dc.subjectrobot-
Título: dc.titleSpaceYNet: A Novel Approach to Pose and Depth-Scene Regression Simultaneously-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.