Multi-sensor 3D object dataset for object recognition with full pose estimation

Please use this identifier to cite or link to this item: http://hdl.handle.net/10045/66422
Información del item - Informació de l'item - Item information
Title: Multi-sensor 3D object dataset for object recognition with full pose estimation
Authors: Garcia-Garcia, Alberto | Orts-Escolano, Sergio | Oprea, Sergiu | Garcia-Rodriguez, Jose | Azorin-Lopez, Jorge | Saval-Calvo, Marcelo | Cazorla, Miguel
Research Group/s: Robótica y Visión Tridimensional (RoViT) | Informática Industrial y Redes de Computadores
Center, Department or Service: Universidad de Alicante. Departamento de Tecnología Informática y Computación | Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial
Keywords: 3D computer vision | Object recognition | 3D object dataset | Kinect V2 | PrimeSense Carmine
Knowledge Area: Arquitectura y Tecnología de Computadores | Ciencia de la Computación e Inteligencia Artificial
Issue Date: May-2017
Publisher: Springer London
Citation: Neural Computing and Applications. 2017, 28(5): 941-952. doi:10.1007/s00521-016-2224-9
Abstract: In this work, we propose a new dataset for 3D object recognition using the new high-resolution Kinect V2 sensor and some other popular low-cost devices like PrimeSense Carmine. Since most already existing datasets for 3D object recognition lack some features such as 3D pose information about objects in the scene, per pixel segmentation or level of occlusion, we propose a new one combining all this information in a single dataset that can be used to validate existing and new 3D object recognition algorithms. Moreover, with the advent of the new Kinect V2 sensor we are able to provide high-resolution data for RGB and depth information using a single sensor, whereas other datasets had to combine multiple sensors. In addition, we will also provide semiautomatic segmentation and semantic labels about the different parts of the objects so that the dataset could be used for testing robot grasping and scene labeling systems as well as for object recognition.
Sponsor: This work was partially funded by the Spanish Government DPI2013-40534-R Grant. This work has also been funded by the grant “Ayudas para Estudios de Máster e Iniciación a la Investigación” from the University of Alicante.
URI: http://hdl.handle.net/10045/66422
ISSN: 0941-0643 (Print) | 1433-3058 (Online)
DOI: 10.1007/s00521-016-2224-9
Language: eng
Type: info:eu-repo/semantics/article
Rights: © The Natural Computing Applications Forum 2016. The final publication is available at Springer via http://dx.doi.org/10.1007/s00521-016-2224-9
Peer Review: si
Publisher version: http://dx.doi.org/10.1007/s00521-016-2224-9
Appears in Collections:INV - RoViT - Artículos de Revistas
INV - I2RC - Artículos de Revistas

Files in This Item:
Files in This Item:
File Description SizeFormat 
Thumbnail2017_Garcia-Garcia_etal_NeuralComput&Applic_final.pdfVersión final (acceso restringido)3,01 MBAdobe PDFOpen    Request a copy
Thumbnail2017_Garcia-Garcia_etal_NeuralComput&Applic_preprint.pdfPreprint (acceso abierto)17,1 MBAdobe PDFOpen Preview


Items in RUA are protected by copyright, with all rights reserved, unless otherwise indicated.