We present a system for rhythmic analysis of human motion in real-time. Using a combination of both spectral (Fourier) and spatial analysis of onsets, we are able to extract repeating rhythmic patterns from data collected using accelerometers. These extracted rhythmic patterns show the relative magnitudes of accentuated movements and their spacing in time. Inspired by previous work in automatic beat detection of audio recordings, we designed our algorithms to be robust to changes in timing

more »

... multiple analysis techniques and methods for sensor fusion, filtering and clustering. We tested our system using a limited set of movements, as well as dance movements collected from a professional, both with promising results.