A study of the effect of noise and occlusion on the accuracy of convolutional neural networks applied to 3D object recognition
Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10045/72633
Registro completo de metadatos
Campo DC | Valor | Idioma |
---|---|---|
dc.contributor | Informática Industrial y Redes de Computadores | es_ES |
dc.contributor | Robótica y Visión Tridimensional (RoViT) | es_ES |
dc.contributor.author | Garcia-Garcia, Alberto | - |
dc.contributor.author | Garcia-Rodriguez, Jose | - |
dc.contributor.author | Orts-Escolano, Sergio | - |
dc.contributor.author | Oprea, Sergiu | - |
dc.contributor.author | Gomez-Donoso, Francisco | - |
dc.contributor.author | Cazorla, Miguel | - |
dc.contributor.other | Universidad de Alicante. Departamento de Tecnología Informática y Computación | es_ES |
dc.contributor.other | Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial | es_ES |
dc.contributor.other | Universidad de Alicante. Instituto Universitario de Investigación Informática | es_ES |
dc.date.accessioned | 2018-01-19T10:28:57Z | - |
dc.date.available | 2018-01-19T10:28:57Z | - |
dc.date.issued | 2017-11 | - |
dc.identifier.citation | Computer Vision and Image Understanding. 2017, 164: 124-134. doi:10.1016/j.cviu.2017.06.006 | es_ES |
dc.identifier.issn | 1077-3142 (Print) | - |
dc.identifier.issn | 1090-235X (Online) | - |
dc.identifier.uri | http://hdl.handle.net/10045/72633 | - |
dc.description.abstract | In this work, we carry out a study of the effect of adverse conditions, which characterize real-world scenes, on the accuracy of a Convolutional Neural Network applied to 3D object class recognition. Firstly, we discuss possible ways of representing 3D data to feed the network. In addition, we propose a set of representations to be tested. Those representations consist of a grid-like structure (fixed and adaptive) and a measure for the occupancy of each cell of the grid (binary and normalized point density). After that, we propose and implement a Convolutional Neural Network for 3D object recognition using Caffe. At last, we carry out an in-depth study of the performance of the network over a 3D CAD model dataset, the Princeton ModelNet project, synthetically simulating occlusions and noise models featured by common RGB-D sensors. The results show that the volumetric representations for 3D data play a key role on the recognition process and Convolutional Neural Network can be considerably robust to noise and occlusions if a proper representation is chosen. | es_ES |
dc.description.sponsorship | This work has been supported by the Spanish Government DPI2013-40534-R grant for the SIRMAVED project, also supported with FEDER funds. This work has also been funded by the grant “Ayudas para Estudios de Máster e Iniciación a la Investigación” from the University of Alicante. | es_ES |
dc.language | eng | es_ES |
dc.publisher | Elsevier | es_ES |
dc.rights | © 2017 Elsevier Inc. | es_ES |
dc.subject | Deep learning | es_ES |
dc.subject | 3D object recognition | es_ES |
dc.subject | Convolutional neural networks | es_ES |
dc.subject | Noise | es_ES |
dc.subject | Occlusion | es_ES |
dc.subject | Caffe | es_ES |
dc.subject.other | Arquitectura y Tecnología de Computadores | es_ES |
dc.subject.other | Ciencia de la Computación e Inteligencia Artificial | es_ES |
dc.title | A study of the effect of noise and occlusion on the accuracy of convolutional neural networks applied to 3D object recognition | es_ES |
dc.type | info:eu-repo/semantics/article | es_ES |
dc.peerreviewed | si | es_ES |
dc.identifier.doi | 10.1016/j.cviu.2017.06.006 | - |
dc.relation.publisherversion | http://dx.doi.org/10.1016/j.cviu.2017.06.006 | es_ES |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | es_ES |
dc.relation.projectID | info:eu-repo/grantAgreement/MINECO//DPI2013-40534-R | - |
Aparece en las colecciones: | INV - I2RC - Artículos de Revistas INV - RoViT - Artículos de Revistas INV - AIA - Artículos de Revistas |
Archivos en este ítem:
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
2017_Garcia-Garcia_etal_CompVisImageUnderst_final.pdf | Versión final (acceso restringido) | 2,74 MB | Adobe PDF | Abrir Solicitar una copia |
2017_Garcia-Garcia_etal_CompVisImageUnderst_preprint.pdf | Preprint (acceso abierto) | 3,62 MB | Adobe PDF | Abrir Vista previa |
Todos los documentos en RUA están protegidos por derechos de autor. Algunos derechos reservados.