A Novel Tracking Method Based on Optimized Selection

3D hand gesture tracking is one of the key problems in human-computer interface design and has attracted increasing attention as an alternative way to traditional input devices, such as mouses and keyboards. Generally speaking, a human hand, as a typical articulated structure, has 15 joints and high dimensionality with 26DOFs, which makes it very difficult for real time tracking. A novel approach is presented in this paper. Firstly, a basic concept, sigma point, is defined, and the way to acquire the Sigma points of a state variable is presented and further proved in detail. Then, the global human hand tracking algorithm is put forward, which combine Sigma points and optimized selection based upon particle weights. In order to improve robustness to changing light conditions, a new skin model is proposed which is based on skin luminance. At last, our experimental results demonstrate that, compared with the classical particle filtering, our method has the capacity to use smaller number of particles for higher precision.