增强现实应用中基于三维模型的手形追踪

本文介绍了一种基于三维模型的分步迭代法来实现对全局和局部手运动的估计追踪。手部位置由ICP(Iterative Closed point)算法和因式分解法求得的掌形近似。结合自然手运动限制，本文采用基于序列的Monte Carlo算法追踪手指运动。最后采用在姿态估计和手指关节追踪之间的迭代算法得到一个精确的结构估计。实验证实本方法对自然手势运动具有较好的精确性和鲁棒性。

The 3D-Model- based Hand Tracking method in Augmented Reality

Visually capturing human hand motion requires estimating the 3D hand global pose as well as its local finger articulations. This is a challenging task that requires a search in a high dimensional space due to the high degrees of freedom that fingers exhibit and the self occlusions caused by global hand motion. In this paper we propose a divide and conquer approach to estimate both global and local hand motion. By looking into the palm and extra feature points provided by fingers, the hand pose is determined from the palm using Iterative Closed Point (ICP) algorithm and factorization method. The hand global pose serves as the base frame for the finger motion capturing. Noticing the natural hand motion constraints, we propose an efficient tracking algorithm based on sequential Monte Carlo technique for tracking finger motion. To enhance the accuracy, pose estimations and finger articulation tracking are performed in an iterative manner. Our experiments show that our approach is accurate and robust for natural hand movements.