LexToMap: lexical-based topological mapping

Please use this identifier to cite or link to this item: http://hdl.handle.net/10045/74108
Información del item - Informació de l'item - Item information
Title: LexToMap: lexical-based topological mapping
Authors: Rangel, José Carlos | Martínez-Gómez, Jesús | García-Varea, Ismael | Cazorla, Miguel
Research Group/s: Robótica y Visión Tridimensional (RoViT)
Center, Department or Service: Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial | Universidad de Alicante. Instituto Universitario de Investigación Informática
Keywords: Topological mapping | Deep learning | Localization | Image annotations | Lexical labels
Knowledge Area: Ciencia de la Computación e Inteligencia Artificial
Issue Date: 2017
Publisher: Taylor & Francis
Citation: Advanced Robotics. 2017, 31(5): 268-281. doi:10.1080/01691864.2016.1261045
Abstract: Any robot should be provided with a proper representation of its environment in order to perform navigation and other tasks. In addition to metrical approaches, topological mapping generates graph representations in which nodes and edges correspond to locations and transitions. In this article, we present LexToMap, a topological mapping procedure that relies on image annotations. These annotations, represented in this work by lexical labels, are obtained from pre-trained deep learning models, namely CNNs, and are used to estimate image similarities. Moreover, the lexical labels contribute to the descriptive capabilities of the topological maps. The proposal has been evaluated using the KTH-IDOL 2 data-set, which consists of image sequences acquired within an indoor environment under three different lighting conditions. The generality of the procedure as well as the descriptive capabilities of the generated maps validate the proposal.
Sponsor: This work was supported by the Ministerio de Economia y Competitividad of the Spanish Government, supported with Feder funds, under grant DPI2013-40534-R and TIN2015-66972-C5-2-R; Consejería de Educación, Cultura y Deportes of the JCCM regional government under project PPII-2014- 015-P. José Carlos Rangel is also funded by the IFARHU of the Republic of Panamá under grant 8- 2014-166.
URI: http://hdl.handle.net/10045/74108
ISSN: 0169-1864 (Print) | 1568-5535 (Online)
DOI: 10.1080/01691864.2016.1261045
Language: eng
Type: info:eu-repo/semantics/article
Rights: © Taylor & Francis
Peer Review: si
Publisher version: http://dx.doi.org/10.1080/01691864.2016.1261045
Appears in Collections:INV - RoViT - Artículos de Revistas

Files in This Item:
Files in This Item:
File Description SizeFormat 
Thumbnail2017_Rangel_etal_AdvRobotics_revised.pdfVersión revisada (acceso abierto)3,66 MBAdobe PDFOpen Preview

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