Skip navigation
SuUB logo
DSpace logo

  • Home
  • Institutions
    • University of Bremen
    • City University of Applied Sciences
    • Bremerhaven University of Applied Sciences
  • Sign on to:
    • My Media
    • Receive email
      updates
    • Edit Account details

Citation link: https://nbn-resolving.de/urn:nbn:de:gbv:46-00102865-17
00102865-1.pdf
OpenAccess
 
copyright

Model-Based High-Dimensional Pose Estimation with Application to Hand Tracking


File Description SizeFormat
00102865-1.pdf24.62 MBAdobe PDFView/Open
Other Titles: Modellbasierte Erkennung von Objekten mit hochdimensionalem Zustandsraum und der Anwendung auf das Hand Tracking
Authors: Mohr, Daniel 
Supervisor: Zachmann, Gabriel  
1. Expert: Zachmann, Gabriel  
Experts: Klinker, Gudrun  
Abstract: 
This thesis presents novel techniques for computer vision based full-DOF human hand motion estimation. Our main contributions are: A robust skin color estimation approach; A novel resolution-independent and memory efficient representation of hand pose silhouettes, which allows us to compute area-based similarity measures in near-constant time; A set of new segmentation-based similarity measures; A new class of similarity measures that work for nearly arbitrary input modalities; A novel edge-based similarity measure that avoids any problematic thresholding or discretizations and can be computed very efficiently in Fourier space; A template hierarchy to minimize the number of similarity computations needed for finding the most likely hand pose observed; And finally, a novel image space search method, which we naturally combine with our hierarchy. Consequently, matching can efficiently be formulated as a simultaneous template tree traversal and function maximization.
Keywords: Computer Vision; Object Detection; Object Recognition; Tracking; Hand Pose Estimation
Issue Date: 12-Oct-2012
Type: Dissertation
Secondary publication: no
URN: urn:nbn:de:gbv:46-00102865-17
Institution: Universität Bremen 
Faculty: Fachbereich 03: Mathematik/Informatik (FB 03) 
Appears in Collections:Dissertationen

  

Page view(s)

819
checked on May 9, 2025

Download(s)

76
checked on May 9, 2025

Google ScholarTM

Check


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

Legal notice -Feedback -Data privacy
Media - Extension maintained and optimized by Logo 4SCIENCE