Accurate gait modelling based on waveform scaling before DFT

Abstract

Gait modelling is essential for many applications including animation, activity recognition, medical diagnosis, and robotics. Many researchers have worked on mathematically express the movement of human bodies. At the current stage, the reconstructed waveforms from the mathematical expressions either represent smoothened waveforms, noisy, or require a high number of computations. In this study, the thigh and shank angle waveforms are time and amplitude scaled before performing a discrete Fourier transform (DFT). By doing so, the correlation coefficient between the original and reconstructed waveforms can be improved without increasing the number of harmonics. The shank's angular velocity is also recalculated from the reconstructed shank's angle waveform for gait phase detection, and shows accurate results in heel and toe strikes estimation when compared to the original shank's angular velocity. Additionally, the harmonic components of the waveforms are used for gait recognition. Experimental results show that it is useful to time and amplitude-scale the angle waveforms to ‘enlarge’ the distinctive regions of the angle waveforms for better classification accuracy.