Deriving Motion Constraints in Finger Joints of Individualized Hand Model for Manipulation by Data Glove

In this paper, we propose a novel method of skeleton es-timation for the purpose of constructing and manipulating individualized hand models via a data glove. To recon-struct actual hand accurately, we derive motion constraints in fully 6-DOF at the joints without assuming either a cen-ter of rotation or a joint axis. The constraints are derived by regression analysis on the configuration of the finger seg-ments with respect to the sensor data. In order to acquire pairs of the configuration and the sensor data, we introduce graspable reference objects for reproducing postures with and without the data glove. To achieve accurate regression on fewer samples, we introduce a regression model accord-ing to a detailed investigation using a fused motion capture system, which enabled us to perform optical motion capture and sensor data collection simultaneously. The effective-ness of the method is demonstrated through practical appli-cations involving grasped reference objects. 1