Improved estimation of hand postures using depth images

Hand pose estimation is the task of deriving a hand´s articulation from sensory input, here depth images in particular. A novel approach states pose estimation as an optimization problem: a high-dimensional hypothesis space is constructed from a hand model, in which particle swarms search for the best pose hypothesis. We propose various additions to this approach. Our extended hand model includes anatomical constraints of hand motion by applying principal component analysis (PCA). This allows us to treat pose estimation as a problem with variable dimensionality. The most important benefit becomes visible once our PCA-enhanced model is combined with biased particle swarms. Several experiments show that accuracy and performance of pose estimation improve significantly.