On the Use of Postural Synergies to Improve Human Hand Pose Reconstruction

In this paper we consider the problem of estimating the posture of a human hand using sensing gloves, and how to improve their performance by exploiting the knowledge on how humans most frequently use their hands. We consider low-cost gloves providing measurements which are limited under several regards: they are generated through an imperfectly known model, are subject to noise, and are less than the number of degrees of freedom of the hand. Under these conditions, direct reconstruction of the hand pose is an ill-posed problem, and performance is very limited. To obtain an acceptable level of accuracy without modifying the glove hardware, hence basically at no extra cost, we propose to exploit the information on most frequent human hand poses, as represented in a database of postural synergies built beforehand. We discuss how such an a priori information can be fused with glove data in a consistent way, so as to provide a good hand pose reconstruction in spite of insufficient and inaccurate sensing data. Simulations and experiments on a low-cost glove are reported which demonstrate the effectiveness of the proposed techniques.