Por favor, use este identificador para citar o enlazar este ítem: https://ri-ng.uaq.mx/handle/123456789/3397
Registro completo de metadatos
Campo DC Valor Lengua/Idioma
dc.rights.licensehttp://creativecommons.org/licenses/by-nc-nd/4.0es_ES
dc.contributorJesús Carlos Pedraza Ortegaes_ES
dc.creatorEdgar Rodrigo Lopez Silvaes_ES
dc.date2021-09-07-
dc.date.accessioned2022-01-31T17:49:12Z-
dc.date.available2022-01-31T17:49:12Z-
dc.date.issued2021-09-07-
dc.identifiermonoculares_ES
dc.identifierdepthes_ES
dc.identifierlow-latencyes_ES
dc.identifierconvolutionales_ES
dc.identifier.urihttp://ri-ng.uaq.mx/handle/123456789/3397-
dc.descriptionMonocular depth estimation is becoming a very interesting problem in computer vision to solve due to the several tasks that require as an input the spatial structure of a scene, such as 3D reconstruction, 3D object detection, localization and mapping. The most effective techniques for monocular depth estimation are based on large deep learning-based architectures that cannot be deployed on systems with limited computational resources and therefore preventing its use in application fields where the advantages of monocular cameras (i.e., low cost, small size, low weight and low-energy consumption) could also be exploited. Under this context, the research of low-latency deep learning architectures for monocular depth estimation is a very promising topic for which just a few methods have been proposed until now. In this master thesis, a very low-latency fully convolutional network is proposed. The quantitative results on the NYU-Depth V2 dataset show that the proposed method is 1.6x faster than the state-of-the art related method while also reducing the RMSE metric by 1.16%.es_ES
dc.formatAdobe PDFes_ES
dc.language.isoenges_ES
dc.relation.requiresSies_ES
dc.rightsAcceso Abiertoes_ES
dc.subjectOTRASes_ES
dc.titleMonocular Depth Estimation with Convolutional Neural Networks on Embedded Systemses_ES
dc.typeTesis de maestríaes_ES
dc.creator.tidcurpes_ES
dc.contributor.tidcurpes_ES
dc.creator.identificadorLOSE930806HGTPLD05es_ES
dc.contributor.identificadorPEOJ691222HSPDRS07es_ES
dc.contributor.roleDirectores_ES
dc.degree.nameMaestría en Ciencias en Inteligencia Artificiales_ES
dc.degree.departmentFacultad de Ingenieríaes_ES
dc.degree.levelMaestríaes_ES
Aparece en las colecciones: Maestría en Ciencias en Inteligencia Artificial

Ficheros en este ítem:
Fichero Descripción Tamaño Formato  
RI006438.pdf1.89 MBAdobe PDFVista previa
Visualizar/Abrir
Mostrar el registro sencillo del ítem


Los ítems de DSpace están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.