Dynamic Gesture Recognition with Laban Movement Analysis and Hidden Markov Models

In this paper, we propose a new approach for gesture recognition based upon the quantification of Laban Movement Analysis (LMA) concepts. The resulting body features are used to build a dictionary of key poses. Then, a soft assignment method is applied to the gesture sequences to obtain a gesture representation. The assignment results are used as input in a Hidden Markov Models (HMM) scheme for dynamic gesture recognition purposes. The proposed approach achieves high recognition rates (more than 92% for certain categories of gestures), when tested and evaluated on a corpus including 11 different actions. The high recognition rates obtained on two other datasets (Microsoft Gesture dataset [1] and UTKinect-Human Detection dataset [2]) show the relevance of our method.