In this video, we show experimental results to a novel framework for automatically evaluating the quality of 3D tracking results obtained from markerless motion capturing. In our approach, we use inertial sensors to generate suitable reference information. In contrast to previously used marker-based evaluation schemes, inertial sensors are inexpensive, easy to operate, and impose comparatively weak additional constraints on the overall recording setup with regard to location, recording volume, and illumination.
Details can be found in the paper
Analyzing and Evaluating Markerless Motion Tracking Using Inertial Sensors
by Andreas Baak, Thomas Helten, Meinard Müller, Gerard Pons-Moll, Bodo Rosenhahn, and Hans-Peter Seidel, 3rd Workshop on Human Motion, in Conjunction with ECCV 2010.
"Markerless" Motion Tracking ? .. is this real ? wich software?
;
youmasora 2 months ago