A Wearable Gait Monitoring System for 17 Gait Parameters Based on Computer Vision

Abstract

We demonstrate a shoe-mounted gait monitoring system capable of tracking up to 17 gait parameters, including step length, step time, stride velocity, among others. The system employs a stereo camera mounted on one shoe to track a marker placed on the opposite shoe, enabling the estimation of spatial gait parameters. Additionally, a force sensitive resistor (FSR) affixed to the heel of the shoe, combined with a custom-designed algorithm, is utilized to measure temporal gait parameters. Through testing on multiple participants and comparison with a gait mat, our gait monitoring system exhibited excellent performance, with all 17 gait parameters exceeding 93.61% in measurement accuracy. The system also demonstrated a low drift of 4.89% during long walking sessions. A gait identification task conducted on participants using a trained transformer model achieved 95.7% accuracy on the dataset collected by our system, indicating the potential of our system to collect long-sequence, varied gait data suitable for training current large language models (LLMs). The system is cost-effective, user-friendly, and well-suited for real-life measurements.

Keywords: Computer Vision; Gait Identification; Gait Monitoring; Stereo Camera; Transformer Model; Wearable Device.