# Gait Analysis Using Walking-Generated Acceleration Obtained from Two Sensors Attached to the Lower Legs

## TL;DR

This paper introduces a new gait analysis method using lower leg sensors to separate motion-related accelerations from gravitational effects.

## Contribution

A novel gait analysis method that isolates walking-generated accelerations using sensor fusion and coordinate system calculations.

## Key findings

- Sensor fusion estimates sensor pose to calculate gravitational acceleration components.
- Translational acceleration is derived by subtracting gravitational, centrifugal, and tangential accelerations from raw sensor data.
- The method isolates accelerations caused by walking motion, improving gait evaluation accuracy.

## Abstract

Gait evaluation approaches using small, lightweight inertial sensors have recently been developed, offering improvements in terms of both portability and usability. However, accelerometer outputs include both the acceleration that is generated by human motion and gravitational acceleration, which changes along with the posture of the body part to which the sensor is attached. This study presents a gait analysis method that uses the gravitational, centrifugal, tangential, and translational accelerations obtained from sensors attached to the lower legs. In this method, each sensor pose is sequentially estimated using sensor fusion to combine data obtained from a three-axis gyroscope, a three-axis accelerometer, and a three-axis magnetometer. The estimated sensor pose is then used to calculate the gravitational acceleration that is included in each axis of the sensor coordinate system. The centrifugal and tangential accelerations are determined from the gyroscope output. The translational acceleration is then obtained by subtracting the centrifugal, tangential, and gravitational accelerations from the accelerometer output. As a result, the acceleration components contained in the outputs of the accelerometers attached to the lower legs are provided. As only the acceleration components caused by walking motion are captured, thus reflecting their characteristics, it is expected that the developed method can be used for gait evaluation.