IMU Based Deep Stride Length Estimation With Self-Supervised Learning

TL;DR

This paper introduces a self-supervised deep learning approach using a CNN to estimate stride length and classify gait type from IMU data, reducing calibration needs and improving accuracy over traditional methods.

Contribution

It presents a novel CNN model trained with self-supervised learning on unlabeled data for improved stride length estimation and gait classification.

Findings

Achieves 4.78% error in stride length estimation

99.83% accuracy in gait classification

Outperforms previous methods with 7.44% error

Abstract

Stride length estimation using inertial measurement unit (IMU) sensors is getting popular recently as one representative gait parameter for health care and sports training. The traditional estimation method requires some explicit calibrations and design assumptions. Current deep learning methods suffer from few labeled data problem. To solve above problems, this paper proposes a single convolutional neural network (CNN) model to predict stride length of running and walking and classify the running or walking type per stride. The model trains its pretext task with self-supervised learning on a large unlabeled dataset for feature learning, and its downstream task on the stride length estimation and classification tasks with supervised learning with a small labeled dataset. The proposed model can achieve better average percent error, 4.78\%, on running and walking stride length regression and 99.83\% accuracy on running and walking classification, when compared to the previous approach, 7.44\% on the stride length estimation.