Creator |
|
|
|
|
Language |
|
Date |
|
Source Title |
|
First Page |
|
Last Page |
|
Publication Type |
|
Access Rights |
|
Related DOI |
|
|
Related URI |
|
|
Relation |
|
|
Abstract |
We are researching for real-time hand shape estimation for natural user interface. We have employed a computer vision approach, since unwired sensing provides restriction-free observation unlike a dat...aglove. Since a human's hand has many joints, it has geometrically high degrees of freedom, which makes hand shape estimation difficult. For example, we have to deal with a self-occlusion problem and a large amount of computation, On the other hand, a human's hand has several constraints at the same time, i.e., each joint has a movable range and interdependence. This paper proposes a novel method to estimate hand shapes in real-time by using both shape features from camera images and hand constraints heuristically introduced. We have mede preliminary experiments using multiple cameras under uncomplicated background. We show experimental results in oder to verify the effectiveness of our proposed method.show more
|