Action trajectory reconstruction from inertial sensor measurements

Inertial sensors, such as accelerometers and gyroscopes, are rarely used by themselves to compute velocity and position as each requires the integration of very noisy data. The variance and bias in the resulting position and velocity estimates grow unbounded in time. This paper proposes a solution to provide a de-biased and de-noised estimation of position and velocity of human actions from accelerometer measurements. The method uses a continuous wavelet transform applied to the measurements recursively to provide reliable action trajectory reconstruction. The results are presented from experiments performed with a MEMS accelerometer and gyroscope.