Model based Full Body Human Motion Reconstruction from Video Data

In proceedings of 6 th International Conference on Computer Vision / Computer Graphics Collaboration Techniques and Applications (MIRAGE 2013), Berlin, Germany, Juni 2013
 

Abstract

This paper introduces a novel framework for full body human motion reconstruction from 2D video data using a motion capture database as knowledge base containing information on how people move. By extracting suitable twodimensional features from both, the input video sequence and the motion capture database, we are able to employ an efficient retrieval technique to run a data-driven optimization. Only little preprocessing is needed by our method, the reconstruction process runs close to real time. We evaluate the proposed techniques on synthetic two-dimensional input data obtained from motion capture data and on real video data.

Bilder

Paper herunterladen

Paper herunterladen

Zusätzliches Material

  • Video (AVI-Video, 16.2 MB)

Bibtex

@INPROCEEDINGS{yasin-2013,
     author = {Yasin, Hashim and Kr{\"u}ger, Bj{\"o}rn and Weber, Andreas},
      title = {Model based Full Body Human Motion Reconstruction from Video Data},
  booktitle = {6 th International Conference on Computer Vision / Computer Graphics Collaboration Techniques and
               Applications (MIRAGE 2013)},
       year = {2013},
      month = jun,
   location = {Berlin, Germany},
   abstract = {This paper introduces a novel framework for full body human
               motion reconstruction from 2D video data using a motion
               capture database as knowledge base containing information
               on how people move. By extracting suitable twodimensional
               features from both, the input video sequence
               and the motion capture database, we are able to employ an
               efficient retrieval technique to run a data-driven optimization.
               Only little preprocessing is needed by our method, the
               reconstruction process runs close to real time. We evaluate
               the proposed techniques on synthetic two-dimensional input
               data obtained from motion capture data and on real video
               data.}
}