Publication,
Research,
Docs and Info,
KAMEDA
We applied our method to an image sequence with a male walking. The
image size 600 by 360 pixels and the sequence includes 40 frames.
is set to 6 degree and 
is 2,500 pixels. The
estimated result is shown in Figure 2. The result
motion is displayed 100 cm right to the actual result location for the
readers. Here you can see that our method keeps tracking the parts in
spite of occlusions. As our method uses a complete human model and can
obtain the joint angles from the image sequence, we can show the
estimation result from any viewpoint. See Figure 3.
Figure 3: Result from Another Viewpoint
