Map Slammer. Densifying Scattered KSLAM 3D Maps with Estimated Depth

Please use this identifier to cite or link to this item: http://hdl.handle.net/10045/94751
Información del item - Informació de l'item - Item information
Title: Map Slammer. Densifying Scattered KSLAM 3D Maps with Estimated Depth
Authors: Torres Cámara, José Miguel
Research Director: Cazorla, Miguel | Gomez-Donoso, Francisco
Center, Department or Service: Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial
Keywords: SLAM | 3D maps | Point clouds | Depth perception | Depth estimation
Knowledge Area: Ciencia de la Computación e Inteligencia Artificial
Issue Date: 27-Jul-2019
Date of defense: 22-Jul-2019
Abstract: There are a range of small-size robots that cannot afford to mount a three-dimensional sensor due to energy, size or power limitations. However, the best localisation and mapping algorithms and object recognition methods rely on a three-dimensional representation of the environment to provide enhanced capabilities. Thus, in this work, a method to create a dense three-dimensional representation of the environment by fusing the output of a keyframe-based SLAM (KSLAM) algorithm with predicted point clouds is proposed. It will be demonstrated with quantitative and qualitative results the advantages of this method, focusing in three different measures: localisation accuracy, densification capabilities and accuracy of the resultant three-dimensional map.
URI: http://hdl.handle.net/10045/94751
Language: eng
Type: info:eu-repo/semantics/bachelorThesis
Rights: Licencia Creative Commons Reconocimiento-NoComercial-SinObraDerivada 4.0
Appears in Collections:Grado en Ingeniería Robótica - Trabajos Fin de Grado

Files in This Item:
Files in This Item:
File Description SizeFormat 
ThumbnailSLAM_usando_tecnicas_de_deep_learning_Torres_Camara_Jose_Miguel.pdf7,18 MBAdobe PDFOpen Preview


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