3-D hand posture recognition by training contour variation
3-D hand posture recognition by training contour variation
复制标题
DOI：
10.1109/afgr.2004.1301647
复制
发表时间：
2004-05
期刊：
影响因子：
--
通讯作者：
Akihiro Imai;N. Shimada;Y. Shirai
中科院分区：
文献类型：
--
作者：
Akihiro Imai;N. Shimada;Y. Shirai
本文提出了一种基于 2D 外观的估计 3D 手势的方法。由于 3D 姿势和视点的变化，传统方法在外观变化方面本质上很弱。这个弱点可以通过注册所有可能的外观来克服，但由于人手的高自由度，它不适合。在该新颖方法中，根据 3D 手模型生成的多个 CG 图像来训练围绕已注册典型外观的可能形状外观（手轮廓）的变化。可能的变化被有效地表示为外观特征空间中的局部压缩特征流形（LCFM）。连续图像的姿势估计是通过跟踪 LCFM 中的姿势来完成的。最后实验结果表明了该方法的有效性。
This paper proposes a 2-D appearance-based method of estimating 3-D hand posture. The conventional methods are essentially weak in appearance changes due to the changes of 3-D postures and viewpoint. This weakness can be overcome by registering all the possible appearances but it is not suitable because of the high DOF of human hand. In the novel method, the variations of possible shape appearances (hand contour) around the registered typical appearances are trained from a number of CG images generated from 3-D hand model. The possible variations are efficiently represented as the locally-compressed feature manifold (LCFM) in an appearance feature space. The posture estimation for the sequential images is done by tracking the posture in the LCFM. Finally the experimental results show the effectiveness of the method.