Gestural Data for Expressive Control: A study in repetition and recognition

Abstract

This thesis presents the explorative research into gesture recognition on unsegmented three-dimensional accelerometer data. The application context is interactive dance and music performance. Repetition of gesture is used to distinguish between gesture and non-gesture. Repetition is detected using an algorithm for pitch detection which is adapted for multi-dimensional time-series called YIN-MD. Three template based gesture recognition algorithms are compared on accuracy performance in different contexts and how they relate to this specific project. Parameter optimization of the YIN-MD algorithm is performed and pre- and post processing methods are applied to optimize the detection accuracy for this project. From the three algorithms GVF, DTW and DTW-PS, the last one is evaluated as the most promising for this project due to high accuracy performance and phase invariance.