English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Conference Paper

Enhancing Silhouette-based Human Motion Capture with 3D Motion Fields

MPS-Authors
/persons/resource/persons45610

Theobalt,  Christian
Computer Graphics, MPI for Informatics, Max Planck Society;
Programming Logics, MPI for Informatics, Max Planck Society;

/persons/resource/persons44222

Carranza,  Joel
Computer Graphics, MPI for Informatics, Max Planck Society;
Graphics - Optics - Vision, MPI for Informatics, Max Planck Society;

/persons/resource/persons44965

Magnor,  Marcus
Graphics - Optics - Vision, MPI for Informatics, Max Planck Society;

/persons/resource/persons45449

Seidel,  Hans-Peter
Computer Graphics, MPI for Informatics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)
There are no public fulltexts available
Supplementary Material (public)
There is no public supplementary material available
Citation

Theobalt, C., Carranza, J., Magnor, M., & Seidel, H.-P. (2003). Enhancing Silhouette-based Human Motion Capture with 3D Motion Fields. In 11th Pacific Conference on Computer Graphics and Applications (PG-03) (pp. 185-193). Los Alamitos, USA: IEEE.


Cite as: http://hdl.handle.net/11858/00-001M-0000-000F-2CDF-B
Abstract
High-quality non-intrusive human motion capture is necessary for acquistion of model-based free-viewpoint video of human actors. Silhouette-based approaches have demonstrated that they are able to accurately recover a large range of human motion from multi-view video. However, they fail to make use of all available information, specifically that of texture information. This paper presents an algorithm that uses motion fields constructed from optical flow in multi-view video sequences. The use of motion fields augments the silhoutte-based method by incorporating texture-information into the tracking process. The algorithm is a key-component in a larger free-viewpoint video system of human actors. Our results demonstrate that our method accurately estimates pose parameters and allows for realistic texture generation in 3D video sequences.