Real-time classification of dance gestures from skeleton animation

Abstract: We present a real-time gesture classification system for skeletal wireframe motion. Its key components include an angular representation of the skeleton designed for recognition robustness under noisy input, a cascaded correlation-based classifier for multivariate time-series data, and a distance metric based on dynamic time-warping to evaluate the difference in motion between an acquired gesture and an oracle for the matching gesture. While the first and last tools are generic in nature and could be applied to any gesture-matching scenario, the classifier is conceived based on the assumption that the input motion adheres to a known, canonical time-base: a musical beat. On a benchmark comprising 28 gesture classes, hundreds of gesture instances recorded using the XBOX Kinect platform and performed by dozens of subjects for each gesture class, our classifier has an average accuracy of 96.9%, for approximately 4-second skeletal motion recordings. This accuracy is remarkable given the input noise from the real-time depth sensor.