Identificador persistente para citar o vincular este elemento: http://hdl.handle.net/10553/117902
Título: Depth-aware convolutional neural networks for accurate 3D pose estimation in RGB-D images
Autores/as: Porzi, Lorenzo
Peñate Sánchez, Adrián 
Ricci, Elisa
Moreno-Noguer, Francesc
Clasificación UNESCO: 1203 Ciencia de los ordenadores
Palabras clave: Neural networks
RGB-D images
Fecha de publicación: 2017
Publicación seriada: IEEE International Conference on Intelligent Robots and Systems. Proceedings
Conferencia: 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017) 
Resumen: Most recent approaches to 3D pose estimation from RGB-D images address the problem in a two-stage pipeline. First, they learn a classifier-typically a random forest-to predict the position of each input pixel on the object surface. These estimates are then used to define an energy function that is minimized w.r.t. the object pose. In this paper, we focus on the first stage of the problem and propose a novel classifier based on a depth-aware Convolutional Neural Network. This classifier is able to learn a scale-adaptive regression model that yields very accurate pixel-level predictions, allowing to finally estimate the pose using a simple RANSAC-based scheme, with no need to optimize complex ad hoc energy functions. Our experiments on publicly available datasets show that our approach achieves remarkable improvements over state-of-the-art methods.
URI: http://hdl.handle.net/10553/117902
ISBN: 978-1-5386-2682-5
ISSN: 2153-0858
DOI: 10.1109/IROS.2017.8206469
Fuente: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 17418330 (24-28 September 2017)
Colección:Actas de congresos
Adobe PDF (3,13 MB)
Vista completa

Google ScholarTM

Verifica

Altmetric


Comparte



Exporta metadatos



Los elementos en ULPGC accedaCRIS están protegidos por derechos de autor con todos los derechos reservados, a menos que se indique lo contrario.