Orientation-Invariant Spatio-Temporal Gait Analysis Using Foot-Worn Inertial Sensors

Abstract

Inertial sensors can potentially assist clinical decision making in gait-related disorders. Methods for objective spatio-temporal gait analysis usually assume the careful alignment of the sensors on the body, so that sensor data can be evaluated using the body coordinate system. Some studies infer sensor orientation by exploring the cyclic characteristics of walking. In addition to being unrealistic to assume that the sensor can be aligned perfectly with the body, the robustness of gait analysis with respect to differences in sensor orientation has not yet been investigated—potentially hindering use in clinical settings. To address this gap in the literature, we introduce an orientation-invariant gait analysis approach and propose a method to quantitatively assess robustness to changes in sensor orientation. We validate our results in a group of young adults, using an optical motion capture system as reference. Overall, good agreement between systems is achieved considering an extensive set of gait metrics. Gait speed is evaluated with a relative error of −3.1±9.2 cm/s, but precision improves when turning strides are excluded from the analysis, resulting in a relative error of −3.4±6.9 cm/s. We demonstrate the invariance of our approach by simulating rotations of the sensor on the foot.

A Deep Learning Approach for Foot Trajectory Estimation in Gait Analysis Using Inertial Sensors

“…The dataset thoroughly described in [28] was used in this study. It consisted of acceleration and angular rate-measured by two inertial measurement units (IMUs)-, and marker trajectories acquired by an optical motion capture system (Vicon, Oxford Metrics).…”

“…These periods were identified using a threshold-based approach-applied to the velocity of the centroid of heel and toe trajectories-, as described in [10]. These periods were used to estimate the vector normal to the horizontal plane of movement-resorting to Principal Component Analysis (PCA)-, which was used to calibrate the lab's horizontal plane, as described in [28].…”

“…Foot contact (FC) and foot off (FO) events were detected from local minima and maxima occurring on vertical heel velocity and vertical toe acceleration, using the method described in [10]. Before detecting gait events, trajectories were low pass filtered using a zero-lag bidirectional first order Butterworth filter (cutoff of 20 Hz) [28].…”

“…Temporal gait parameters-stride, stance, and swing duration-were obtained from FC and FO events. Cadence was calculated as the inverse of stride duration, in units of steps per minute [28]. Spatial gait parameters-stride length (SL), swing width (SW), and minimum toe clearance (MTC)-were calculated as illustrated in Figure 2, using the trajectories of the heel and toe.…”

“…Spatial gait parameters-stride length (SL), swing width (SW), and minimum toe clearance (MTC)-were calculated as illustrated in Figure 2, using the trajectories of the heel and toe. Gait speed was obtained by dividing stride length by its corresponding stride duration [28].…”