Three-dimensional gait estimation and prediction using particle filters

Abstract

This paper introduces a newly proposed gait recognition algorithm and demonstrates its feasibility. The purpose of this study is to solve the problems existing in existing recognition methods and to analyze the motion of a pedestrian in a non-contact and relatively simple way. As a result, the proposed model was formed by modeling the user's torso and both legs and estimating their respective center points. A distance sensor was used as the measurement device, and some of the problems of existing recognition methods were taken into account. In addition, by forming the model, the posture during walking can also be recognized, enabling more accurate recognition. From this point on, the improvement is aimed at how to improve recognition and to show the effectiveness of the model for walking. The developed interface, when combined with actual welfare equipment such as a walker, will contribute to ease of use and the ability to adapt to each individual's gait.