基于深度相机的手腕识别与掌心估测算法(HHME2013-ID51)

当手和手臂都进入深度相机所设定的有效深度范围时，它们将被作为一个整体来提取，若处理时也把它们作为一个整体，这可能会影响手势交互的一些重要算法，如掌心估测，手朝向估测，手的跟踪等。本文分析了手腕的运动特征和手的轮廓特点，并利用内切矩形的几何特征，提出了手腕识别算法来分割手与手臂；为了提高掌心估测算法的性能，本文分析了锐角三角形和最大内切圆的几何特征，并结合手势交互的特点，提出了新的掌心估测算法。经实验证明，手腕识别算法能较好地分割出手与手臂，新的掌心估测算法较之原算法在性能上有显著提高。

The recognition and the center of palm estimation based on depth camera

When the hand and the forearm enter the available depth range of the depth camera, the data of the hand and the forearm will be extracted together. If process these data as a whole, which maybe affect some important algorithms such as the center of palm estimation, the orientation of hand estimation and hand tracing. The paper analyzes the motion features of the wrist and the contour features of the hand, takes advantage of the geometric characteristics of an inscribed rectangle and proposes a wrist recognition algorithm. In order to reduce the computing time of estimating the center of the palm, the paper analyzes the geometric characteristics of an acute triangle and an inscribed circle, combines the features of the hand interaction and proposes a new algorithm of estimating the center of palm. Proved by the experiments, the wrist recognition algorithm can separate the hand from the forearm well, and the new algorithm of estimating the center of the palm has a distinct advantage over the original algorithms in the performance.