• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Real-time Stereo-Image Stitching Using GPU-based Belief Propagation
 
  • Details
  • Full
Options
2009
Conference Paper
Title

Real-time Stereo-Image Stitching Using GPU-based Belief Propagation

Abstract
Image stitching or mosaicing is a challenging vision problem, especially when considering aspects like high definition content, real-time, and proper compensation of the parallax error of objects at different distances to the camera system. Today many approaches to image stitching exist, most of them deal with medium resolution images, offline processing, or are restricted to objects at similar distance. Our approach is based on calculation of disparities between corresponding points in stereo images by employing standard belief propagation. Instead of computing depth-maps like in previous approaches, we compute stitch-maps modifying cost functions in the underlying Markov random field model, which makes further projection steps dispensable and thereby overall computation more efficient. Our GPU-based implementation is real-time capable, allowing to stitch high definition images at constant frame rates. We show exemplary results from our system to demonstrate the quality of the merged images.
Author(s)
Adam, Michael  
Fraunhofer-Institut für Graphische Datenverarbeitung IGD  
Jung, Christoph
Fraunhofer-Institut für Graphische Datenverarbeitung IGD  
Roth, Stefan
TU Darmstadt GRIS
Brunnett, Guido
TU Chemnitz
Mainwork
Vision, Modeling, and Visualization Workshop 2009. Proceedings  
Conference
Workshop Vision, Modeling, and Visualization (VMV) 2009  
Language
English
Fraunhofer-Institut für Graphische Datenverarbeitung IGD  
Keyword(s)
  • image fusion

  • low level image processing

  • General Purpose Computation on Graphics Processing Unit (GPGPU)

  • stereo camera systems

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024