Design of an experimental platform of gait analysis with ActiSense and StereoPi

Abstract

Gait analysis is a systematic study of human movement. Combining wearable foot pressure sensors and machine learning (ML) solutions for a high-fidelity body pose tracking from RGB video frames could reveal more insights into gait abnormalities. However, accurate detection of heel strike (HS) and toe-off (TO) events is crucial to compute interpretable gait parameters. In this work, we present an experimental platform to study the timing of gait events using a new wearable foot pressure sensor (ActiSense System, IEE S.A., Luxembourg), and Google’s open-source ML solution MediaPipe Pose. For this purpose, two StereoPi systems were built to capture stereoscopic videos and images in real time. MediaPipe Pose was applied to the synchronized StereoPi cameras, and two algorithms (ALs) were developed to detect HS and TO events for gait and analysis. Preliminary results from a healthy subject walking on a treadmill show a mean relative deviation across all time spans of less than 4% for the ActiSense device and less than 16% for AL2 (33% for AL1) employing MediaPipe Pose on StereoPi videos. Finally, this work offers a platform for the development of sensor- and video-based ALs to automatically identify the timing of gait events in healthy individuals and those with gait disorders.

Keywords

• human gait
• risk of falls
• computer vision
• pose estimation
• stereoscopic cameras
• foot pressure insoles