Automatic hoof-on and -off detection in horses using hoof-mounted inertial measurement unit sensors

Abstract

For gait classification, hoof-on and hoof-off events are fundamental locomotion characteristics of interest. These events can be measured with inertial measurement units (IMUs) which measure the acceleration and angular velocity in three directions. The aim of this study was to present two algorithms for automatic detection of hoof-events from the acceleration and angular velocity signals measured by hoof-mounted IMUs in walk and trot on a hard surface. Seven Warmblood horses were equipped with two wireless IMUs, which were attached to the lateral wall of the right front (RF) and hind (RH) hooves. Horses were walked and trotted on a lead over a force plate for internal validation. The agreement between the algorithms for the acceleration and angular velocity signals with the force plate was evaluated by Bland Altman analysis and linear mixed model analysis. These analyses were performed for both hoof-on and hoof-off detection and for both algorithms separately. For the hoof-on detection, the angular velocity algorithm was the most accurate with an accuracy between 2.39 and 12.22 ms and a precision of around 13.80 ms, depending on gait and hoof. For hoof-off detection, the acceleration algorithm was the most accurate with an accuracy of 3.20 ms and precision of 6.39 ms, independent of gait and hoof. These algorithms look highly promising for gait classification purposes although the applicability of these algorithms should be investigated under different circumstances, such as different surfaces and different hoof trimming conditions.

Automatic methods of hoof-on and -off detection in horses using wearable inertial sensors during walk and trot on asphalt, sand and grass

“…The first novel method estimated hoof-on and -off using Acc R of either the pastern (M1 p ) or cannon (M1 c ). At the level of the hoof, peaks in Acc R are created by the hoof-surface impact (hoof-on) and subsequent hoof lift-off (hoof-off) [13]. Here, it is hypothesised that these peaks in acceleration, which correspond to the gait events, would be detectable at the more proximal locations of the pasterns and cannons.…”

“…The second novel method estimated hoof-on and -off using AngVel R recorded at the pastern (M2 p ) mounted sensors. Tijssen et al [13] reported that spikes in AngVel R recorded at the hoof coincide with hoof-on and -off. Here, the hoof wall can be considered a rigid structure meaning there would be no angular movement of the hoof relative to the solid ground during stance phases.…”

“…a force plate) for fore-and hindlimb gait events at walk and trot. Accuracies in the range of 2.4ms to 12.2ms for hoof-on and 3.2ms for hoofoff were reported [13].…”

“…2.3.1 Reference method. Data from hoof mounted IMUs were processed as per Tijssen et al [13] and gait event timings determined using this method (M ref ) were used as the reference values against which to compare those obtained using other methods. M ref was previously robustly validated against a gold standard, (i.e.…”

“…Tijssen et al [13] reported that IMUs attached to the lateral hoof wall were capable of successfully identifying gait events, using linear accelerations and angular velocities. Distinctive peaks in the resultants of acceleration and angular velocity were found to coincide with instances of hoof-on and -off recorded simultaneously by a force plate.…”