A Study on High Accuracy Stride Estimation on Smartphone Combining Acceleration Sensor and Gyro Sensor

DOI

10.2991/jrnal.2018.5.2.2How to use a DOI?

Keywords

Locomotive Syndrome; Acceleration sensor; Gyro Sensor; Stride Estimation Method; Smartphone

Abstract

The stride is an important parameter in human motion analysis and has been extensively studied by many researchers. This paper focuses on smartphones that are popular in the world, regardless of the measurement environment. In previous research, the stride estimation using the acceleration sensor or the gyro sensor mounted on the smartphone had been studied. However, the stride estimation accuracy has an error rate of about over 10 %. In this paper, we propose a highly accurate stride estimation method using stride correction parameter obtained from cross section movement in addition to conventional sagittal surface stride using acceleration sensor and gyro sensor mounted on a smartphone. Based on the testing results, the error rate of our proposed method with the stride estimated by the Kinect sensor (RGB-D sensor) as the true value was about 6%. It makes possible to estimate the stride with high accuracy.

Copyright

Copyright © 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article under the CC BY-NC license (http://creativecommons.org/licences/by-nc/4.0/).

Download article (PDF)
View full text (HTML)

TY  - JOUR
AU  - Hiroki Tamura
AU  - Keiko Sakurai
AU  - Koichi Tanno
PY  - 2018
DA  - 2018/09/30
TI  - A Study on High Accuracy Stride Estimation on Smartphone Combining Acceleration Sensor and Gyro Sensor
JO  - Journal of Robotics, Networking and Artificial Life
SP  - 83
EP  - 88
VL  - 5
IS  - 2
SN  - 2352-6386
UR  - https://doi.org/10.2991/jrnal.2018.5.2.2
DO  - 10.2991/jrnal.2018.5.2.2
ID  - Tamura2018
ER  -