Ir al contenido (pulsa Retorno)

Universitat Politècnica de Catalunya

    • Català
    • Castellano
    • English
    • LoginRegisterLog in (no UPC users)
  • mailContact Us
  • world English 
    • Català
    • Castellano
    • English
  • userLogin   
      LoginRegisterLog in (no UPC users)

UPCommons. Global access to UPC knowledge

Banner header
66.329 UPC academic works
You are here:
View Item 
  •   DSpace Home
  • Treballs acadèmics
  • Màsters oficials
  • Màster universitari en Automàtica i Robòtica
  • View Item
  •   DSpace Home
  • Treballs acadèmics
  • Màsters oficials
  • Màster universitari en Automàtica i Robòtica
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

3D pose estimation using convolutional neural networks

Thumbnail
View/Open
Report (15,77Mb)
  View Usage Statistics
  LA Referencia / Recolecta stats
Cita com:
hdl:2117/85580

Show full item record
Rubio Romano, Antonio
Tutor / directorMoreno-Noguer, FrancescMés informació; Villamizar Vergel, Michael Alejandro
Document typeMaster thesis
Date2015-10
Rights accessOpen Access
Attribution-NonCommercial-NoDerivs 3.0 Spain
Except where otherwise noted, content on this work is licensed under a Creative Commons license : Attribution-NonCommercial-NoDerivs 3.0 Spain
Abstract
The present Master Thesis describes a new Pose Estimation method based on Convolutional Neural Networks (CNN). This method divides the three-dimensional space in several regions and, given an input image, returns the region where the camera is located. The first step is to create synthetic images of the object simulating a camera located at di↵erent points around it. The CNN is pre-trained with these thousands of synthetic images of the object model. Then, we compute the pose of the object in hundreds of real images, and apply transfer learning with these labeled real images over the existing CNN, in order to refine the weights of the neurons and improve the network behaviour against real input images. Along with this deep learning approach, other techniques have been used trying to improve the quality of the results, such as the classical sliding window or a more recent class-generic object detector called objectness. It is tested with a 2D-model in order to ease the labeling process of the real images. This document outlines all the steps followed to create and test the method, and finally compares it against a state-of-the-art method at di↵erent scales and levels of blurring.
SubjectsNeural networks (Computer science), Image processing, Three-dimensional display systems, Xarxes neuronals (Informàtica), Imatges -- Processament, Visualització tridimensional (Informàtica)
URIhttp://hdl.handle.net/2117/85580
Collections
  • Màsters oficials - Màster universitari en Automàtica i Robòtica [205]
  View Usage Statistics

Show full item record

FilesDescriptionSizeFormatView
Antonio Rubio R ... Estimation Using CNNs.pdfReport15,77MbPDFView/Open

Browse

This CollectionBy Issue DateAuthorsOther contributionsTitlesSubjectsThis repositoryCommunities & CollectionsBy Issue DateAuthorsOther contributionsTitlesSubjects

© UPC Obrir en finestra nova . Servei de Biblioteques, Publicacions i Arxius

info.biblioteques@upc.edu

  • About This Repository
  • Contact Us
  • Send Feedback
  • Privacy Settings
  • Inici de la pàgina