Documents and Info
Three Dimensional Pose Estimation of an Articulated
Object from its Silhouette Image
Yoshinari KAMEDA, Michihiko MINOH, Katsuo IKEDA
We propose a model-matching method to estimate the pose of an
articulated object from only one silhouette image. It assumes that the
object's shape information and the camera calibration parameters have
been given to the system in advance. We first show a contour based
method and then apply it to the pose estimation of a real-life object.
The method presented here has been tested on several silhouettes,
including both computer generated and real-life humans.
Thu Apr 3 22:11:48 JST 1997