Nonparametric density estimation with adaptive anisotropic kernels for human motion tracking

Abstract: In this paper, we suggest to model priors on human motion by means of nonparametric kernel densities. Kernel densities avoid assumptions on the shape of the underlying distribution and let the data speak for themselves. In general, kernel density estimators suffer from the problem known as the curse of dimensionality, i.e., the amount of data required to cover the whole input space grows exponentially with the dimension of this space. In many applications, such as human motion tracking, though, this problem turns out to be less severe, since the relevant data concentrate in a much smaller subspace than the original high-dimensional space. As we demonstrate in this paper, the concentration of human motion data on lower-dimensional manifolds, approves kernel density estimation as a transparent tool that is able to model priors on arbitrary mixtures of human motions. Further, we propose to support the ability of kernel estimators to capture distributions on lowdimensional manifolds by replacing the standard isotropic kernel by an adaptive, anisotropic one.