A three-dimensional representation method for noisy point clouds based on growing self-organizing maps accelerated on GPUs

Empreu sempre aquest identificador per citar o enllaçar aquest ítem http://hdl.handle.net/10045/36484
Información del item - Informació de l'item - Item information
Títol: A three-dimensional representation method for noisy point clouds based on growing self-organizing maps accelerated on GPUs
Autors: Orts-Escolano, Sergio
Director de la investigació: Garcia-Rodriguez, Jose | Cazorla, Miguel
Centre, Departament o Servei: Universidad de Alicante. Departamento de Tecnología Informática y Computación
Paraules clau: 3D representation method | Growing neural gas | Self-organizing maps | Topology preservation | Parallel computing | CUDA | Real-time | Point cloud | 3D reconstruction | GPGPU | RGBD | Noisy 3D data | Object recognition
Àrees de coneixement: Arquitectura y Tecnología de Computadores
Data de creació: 2013
Data de publicació: 2014
Data de lectura: 21-de gener-2014
Editor: Universidad de Alicante
Resum: The research described in this thesis was motivated by the need of a robust model capable of representing 3D data obtained with 3D sensors, which are inherently noisy. In addition, time constraints have to be considered as these sensors are capable of providing a 3D data stream in real time. This thesis proposed the use of Self-Organizing Maps (SOMs) as a 3D representation model. In particular, we proposed the use of the Growing Neural Gas (GNG) network, which has been successfully used for clustering, pattern recognition and topology representation of multi-dimensional data. Until now, Self-Organizing Maps have been primarily computed offline and their application in 3D data has mainly focused on free noise models, without considering time constraints. It is proposed a hardware implementation leveraging the computing power of modern GPUs, which takes advantage of a new paradigm coined as General-Purpose Computing on Graphics Processing Units (GPGPU). The proposed methods were applied to different problem and applications in the area of computer vision such as the recognition and localization of objects, visual surveillance or 3D reconstruction.
URI: http://hdl.handle.net/10045/36484
Idioma: eng
Tipus: info:eu-repo/semantics/doctoralThesis
Apareix a la col·lecció: Tesis doctorals

Arxius per aquest ítem:
Arxius per aquest ítem:
Arxiu Descripció Tamany Format  
Thumbnailtesis_sergio_orts_escolano.pdf31,63 MBAdobe PDFObrir Vista prèvia

Aquest ítem està subjecte a una llicència de Creative Commons Llicència Creative Commons Creative Commons