This paper investigates the estimate of motion parameters from 3D hand joint positions. We formulate the issue as an inverse kinematics problem with biomechanical constraints and propose a fast and robust iterative approach to address the constrained optimization. It elaborately designs a coordinate descent algorithm to decompose the problem into a sequence of decisions on the transformation around each kinematic node (i.e., joint), while the decision for each node is equivalent to a point matching problem. Addressing the whole optimization then amounts to considering all nodes of the kinematic tree from its root to leaves one by one. This not only accelerates the process but also improves the accuracy of the solution of the inverse kinematic optimization. Experiments show that our approach is able to yield results comparable to and even better than those by the state-of-the-art methods.

本文研究了从 3D 手关节位置估计运动参数。我们将该问题表述为具有生物力学约束的逆运动学问题，并提出了一种快速且稳健的迭代方法来解决约束优化问题。它精心设计了坐标下降算法，将问题分解为围绕每个运动学节点（即关节）变换的决策序列，而对每个节点的决策相当于一个点匹配问题。解决整个优化就等于考虑了运动树从根到叶的所有节点。这不仅加速了过程，而且提高了逆运动学优化解的精度。