Arm gesture recognition and humanoid imitation using functional principal component analysis

Abstract

A method is proposed for gesture recognition and humanoid imitation based on Functional Principal Component Analysis (FPCA). FPCA is a statistical technique of functional data analysis that has never been applied before for humanoid imitation. In functional data analysis data (e.g. gestures) are functions that can be considered as observations of a random variable on a functional space. FPCA is an extension of multivariate PCA that provides functional principal components which describe the modes of variation in the data. In the proposed approach FPCA is used for both unsupervised clustering of training data and gesture recognition. In this work we focus on arm gesture recognition. Human hand paths in Cartesian space are reconstructed from inertial sensors. Recognized gestures are reproduced by a small humanoid robot. The FPCA algorithm has also been compared to a state of the art algorithm for gesture classification based on Dynamic Time Warping (DTW). Results indicate that, in this domain, the FPCA algorithm achieves a comparable recognition rate while it outperforms DTW in terms of efficiency in execution time.