ETD

Archivio digitale delle tesi discusse presso l'Università di Pisa

Tesi etd-09042012-173540


Tipo di tesi
Tesi di laurea specialistica
Autore
PIRRITANO, LORENZO
URN
etd-09042012-173540
Titolo
Human Silhouette Detection for Occlusion in (Mobile) AR Applications
Dipartimento
SCIENZE MATEMATICHE, FISICHE E NATURALI
Corso di studi
TECNOLOGIE INFORMATICHE
Relatori
relatore Prof. Cignoni, Paolo
Parole chiave
  • Active Contour Models
  • Ubitrack
  • human silhouette segmentation
  • Snakes
  • LBP
  • Augmented Reality
  • AR
  • OpenCV
  • Interactive Graph Cut
  • Graphcut
  • Grabcut
  • Local Binary Pattern
Data inizio appello
12/10/2012
Consultabilità
Non consultabile
Data di rilascio
12/10/2052
Riassunto
This work focuses on the occlusions issue in Augmented Reality (AR) applications, in specific domains in which the AR application runs on a mobile handheld device, the scenario is supposed to be an unknown indoor environment, and the positions of the persons walking through it, are known. The aim of this work is to solve the problem of occlusions between virtual objects and persons moving within the camera view of the handheld device using the knowledge of the positions/shape information of the tracked persons. The challenge of this research, concerns the person’s silhouette extraction as foreground from the image frame, using one or more image processing algorithms.
File