Low-Cost Multisensor Integrated System for Online Walking Gait Detection

A three-dimensional motion capture system is a useful tool for analysing gait patterns during walking or exercising, and it frequently applied in biomechanical studies. However, most of them are expensive. This study designs low-cost detection with high accuracy reliability that an alternative method/equipment the field to widely used commercial system, virtual user concept (Vicon) system. The proposed integrates mass-produced sensors/chips compact size collect kinematic data. Furthermore, x86 mini personal computer (PC) running at 100 Hz classifies data real-time. To guarantee accuracy, embedded algorithm adopts multilayer perceptron (MLP) model rule-based calibration filter classify into five distinct events: heel-strike, foot-flat, heel-off, toe-off, initial-swing. evaluate performance, volunteers requested walk on treadmill regular speed 4.2 km/h while recorded by Vicon simultaneously. relative time error estimated comparing classified events as reference. results show obtains 99.66% smaller (32 ms), demonstrating performs similarly field.