Real-time gait event detection in a real-world environment using a laser-ranging sensor and gyroscope fusion method

Wearable gait event detection (GED) techniques have great potential for clinical applications by aiding the rehabilitation of individuals in their daily living environment. Unlike previous wearable GED techniques, which have been proposed for offline detection or laboratory settings, we aimed to develop a real-time GED system adapted for utilization in the daily living environment.

This study presents a novel GED system in which foot clearance and sagittal angular velocity were incorporated to realize real-time GED in a real-world environment. The accuracy and robustness of the proposed system were validated in a real-world scenario that consisted of complex ground surfaces, i.e. varying inclinations. Forty-three subjects (23-83 years) were included in this study, and a total of 8866 gait cycles were recorded for analysis.

The proposed system demonstrated consistently high performance in detecting toe off (TO) and heel strike (HS) events in indoor and outdoor walking data which was supported by high performance scores. The detection accuracy of the walking data reached 2.59  ±  13.26 ms (indoor) and 3.31  ±  14.78 ms (outdoor) for TO events, 3.36  ±  15.92 ms (indoor) and 3.77  ±  16.99 ms (outdoor) for HS events. The proposed system showed better performance in detection precision than state-of-the-art real-time GED methods.

The proposed system will benefit the development of long-term analysis and intervention techniques for use in clinics and daily living environments.