Submitted by Computer Vision Study Group on 2009, May 6 - 01:291159 views | 0 comments | 6 votes
pdf

Markerless Motion Capture with Unsynchronized Moving Cameras

  • Markerless Motion Capture with Unsynchronized Moving Cameras
claim it Gallery
www.mpi-inf.mpg.de
In this work we present an approach for markerless motion capture (MoCap) of articulated objects, which are recorded with multiple unsynchronized moving cameras. Instead of using fixed (and expensive) hardware synchronized cameras, this approach allows us to track people with off-the-shelf handheld video cameras. To prepare a sequence for motion capture, we first reconstruct the static background and the position of each camera using Structure-from-Motion (SfM). Then the cameras are registered to each other using the reconstructed static background geometry. Camera synchronization is achieved via the audio streams recorded by the cameras in parallel. Finally, a markerless MoCap approach is applied to recover positions and joint configurations of subjects. Feature tracks and dense background geometry are further used to stabilize the MoCap. The experiments show examples with highly challenging indoor and outdoor scenes.
Nils Hasler, Bodo Rosenhahn, Thorsten Thormshlen, Michael Wand, Juergen Gall, Hans-Peter Seidel
CVPR - 2009
IEEE

Traffic Map
  • Delicious
  • Digg
  • Facebook
  • Google
  • Yahoo
Keywords computer vision | CVPR 2009 | Markerless Motion Capture | Unsynchronized Moving Cameras |
Category Computer Science | Engineering |


Added 06 May 2009
Updated 10 Dec 2009
Type Conference
Year 2009
Where CVPR
Authors Nils Hasler (MPI Informatik), Bodo Rosenhahn (University of Hannover), Thorsten Thormshlen (Max Planck Institut Informatik), Michael Wand (Saarland University & Max Planck Institut Informatik), Juergen Gall (BIWI, ETH Zurich), Hans-Peter Seidel (Max Planck Institut Informatik)

Discussion Board (0)