An Inverse Kinematic Solution Based on a Two-Layer Hierarchical Cluster Model

Abstract

This paper proposes an inverse kinematics solution based on a two-layer hierarchical cluster model. It divides a human skeleton into blocks to build a two-layer hierarchical cluster model. Based on the relationship between the end position and angle vectors of joints in the BVH format motion capture data as well as to make the end position vectors of joints into clusters with the K-MEANS cluster method, we then make the angle vectors of each joint into clusters with the nearest-neighbor cluster method. Based on that, the inverse kinematics solution is made with the consistency between frames as the constraint condition. The experiment results show that the method is high accuracy, fast solution speed and strong adaptability.