Self-adaptive step length estimation method based on pedestrian motion state

TL;DR: In this paper, a self-adaptive step length estimation method based on a pedestrian motion state was proposed, which can adapt to different motion states of the pedestrian by adopting a proper step length parameter according to the motion state identification result of the classifier.

Abstract: The invention discloses a self-adaptive step length estimation method based on a pedestrian motion state. The method comprises the following steps: S1, an accelerometer arranged in the intelligent terminal collecting acceleration data and magnetometer data of pedestrians in the moving process; S2, preprocessing data; S3, dividing the period of data; S4, detecting the maximum value and the minimumvalue of the acceleration of each step of the pedestrian, and simultaneously calculating the walking frequency and the acceleration variance of each step of the pedestrian; S5, identifying the motionstate of each step of the pedestrian by the extracted features through a classifier; and S6, estimating the step length of the pedestrian by adopting a proper step length parameter according to the motion state identification result of the classifier. According to the method, a new nonlinear step length model is established to estimate the step length of the pedestrian, and the step length estimation precision is improved. Step length parameters of different motion states of the pedestrian are fitted through a least square method, and proper step length parameters are selected according to themotion state identification result of the classifier, so that the step length estimation model can adapt to different motion states of the pedestrian.