A vision-based hand motion parameter capturing for HCI

Abstract

In this paper, we develop a real-time motion capturing system. Based on 3-D hand model with structural constraint and kinematical constraint, we may estimate human hand state in high degree of freedom space by using the proposed separable statebased particle filter (SSBPF). We separate the states of the variable and track five different fingers individually by using the particle filter. Combining the hand model and SSBPF, we implement a human hand gesture reconstruction system