Invariant Heel Strike Detection using Gait Motion

Abstract

In visual surveillance and biomedical field, the detecting heel strike position is a basic step for analyzing human behaviors, condition, and gait since due to its capabilities to provide gait stride, step length, walking speed/direction, and walking pattern. This paper presents a novel method for estimating the heel strike position based on analyzing the gait motion regardless of the walking speed and direction. Generally, when a person walks there is known torso movement in the vertical direction. This gait trajectory is a cue to calculate the gait period and the heel strike position. The trajectory can be analyzed by Wavelet decomposition to detect the gait periodicity and the moment of heel strike. Using the above information and known prior knowledge of the gait, a 3D gait trajectory model is constructed to estimate the accurate heel strike event. We evaluate our new approach using the different type of databases and show that we can indeed determine the heel strike position to good effect, including analysis of the scene of crime data. The contributions of this research are that we develop a new gait period detection method by wavelet decomposition and a new strategy which detects the heel strike position based on the human gait movement.