Multisensor-Fusion for 3D Full-Body Human Motion Capture

Authors: Gerard Pons-Moll, Andreas Baak, Thomas Helten, Meinard Mueller, Hans-Peter Seidel, Bodo Rosenhahn

Leibniz University Hannover & Saarland University and MPI Informatik

IEEE Conference on Computer Vision and Pattern Recognition (CVPR'10), San Francisco, CA, USA

Abstract:
In this video we present an approach to fuse video with
orientation data obtained from extended inertial sensors
to improve and stabilize full-body human motion capture.
Even though video data is a strong cue for motion analy-
sis, tracking artifacts occur frequently due to ambiguities
in the images, rapid motions, occlusions or noise. As a
complementary data source, inertial sensors allow for drift-
free estimation of limb orientations even under fast motions.
However, accurate position information cannot be obtained
in continuous operation. Therefore, we propose a hybrid
tracker that combines video with a small number of inertial
units to compensate for the drawbacks of each sensor type:
on the one hand, we obtain drift-free and accurate position
information from video data and, on the other hand, we ob-
tain accurate limb orientations and good performance un-
der fast motions from inertial sensors. In several experi-
ments we demonstrate the increased performance and sta-
bility of our human motion tracker.

Project Page and Data:
http://wwwintern/project/MPI08_Database/

Category:

Science & Technology

Tags:

• CVPR
• Motion
• Capture
• Sensor
• Fusion
• Animation
• Computer
• Vision
• Science

[designertjp]

Nice work you guys are doing! Your research will definitely take 3D Character Animation to the next level with realistic motion capture. I'm a Special Effects Costumer. Would my stretchy Full Cover Video Suit help to reduce the "noise and artifacts" you mention in your project report?