EquiMoves: A Wireless Networked Inertial Measurement System for Objective Examination of Horse Gait

Abstract

In this paper, we describe and validate the EquiMoves system, which aims to support equine veterinarians in assessing lameness and gait performance in horses. The system works by capturing horse motion from up to eight synchronized wireless inertial measurement units. It can be used in various equine gait modes, and analyzes both upper-body and limb movements. The validation against an optical motion capture system is based on a Bland–Altman analysis that illustrates the agreement between the two systems. The sagittal kinematic results (protraction, retraction, and sagittal range of motion) show limits of agreement of ±2.3 degrees and an absolute bias of 0.3 degrees in the worst case. The coronal kinematic results (adduction, abduction, and coronal range of motion) show limits of agreement of −8.8 and 8.1 degrees, and an absolute bias of 0.4 degrees in the worst case. The worse coronal kinematic results are most likely caused by the optical system setup (depth perception difficulty and suboptimal marker placement). The upper-body symmetry results show no significant bias in the agreement between the two systems; in most cases, the agreement is within ±5 mm. On a trial-level basis, the limits of agreement for withers and sacrum are within ±2 mm, meaning that the system can properly quantify motion asymmetry. Overall, the bias for all symmetry-related results is less than 1 mm, which is important for reproducibility and further comparison to other systems.

A Method to Estimate Horse Speed per Stride from One IMU with a Machine Learning Method

“…The accuracy aim for the developed model is 0.6 m/s (36 m/min) in order to meet the expectations of the show jumping professionals. As far as the authors know, this accuracy was not reached for horses by the previous mentioned [1,12] methods using data from one IMU only. The results obtained with this new model will be compared to those of one signal based method, already used for speed estimation in animal locomotion, the overall dynamic body acceleration.…”

“…The presented model cannot be benchmarked to other works on horses because no one else has provided a speed per stride estimation. As a matter of fact, the work in [1,12] calculated traveled distance with preciseness, but the work in [12] aimed to provide a speed estimation in future work. In human research, a wide literature exists on computing human walking speed from data collected by one IMU placed on the foot, as for example [29], who compared two methods of walking speed estimation, whose ARMSE range was 0.2-0.3 km/h (0.06-0.08 m/s) depending on the walking speed and the method used.…”

“…Firstly are the model based methods, like inverted pendulum models for speed estimation in human gait, which simplify complex biomechanical behaviors with a simple mechanical model and incorporate subject specific information like the limb length [9,10]. Secondly are the signal based methods, which mainly rely on signal integration [11] and use signal processing methods like the Butterworth filter to prevent drifting [12]. Those methods need to formulate some realistic assumptions to correct sensors' drift and need a zero velocity phase within each stride to be able to apply the integration process.…”

Automated Step Detection in Inertial Measurement Unit Data From Turkeys

“…There was no golden standard system applied next to the IMU sensor. In experimental settings, optical motion tracking systems are often used as golden standard to test the IMU performance (e.g., Seel et al, 2014;Kluge et al, 2017;Bosch et al, 2018). Here, we used subjective annotation by a person to define the step start and end positions in the IMU profiles knowing that the animals underwent a walking test.…”

Hiding in the deep : online animal activity recognition using motion sensors and machine learning

“…Therefore, placing the sensor on the neck allowed us to use the same sensor on the subjects throughout the day without the need to switch them between different types of horse-equipment. When high quality gait analysis is required, it might be better to use multiple sensors locations simultaneously, including the legs [22,170]. However, our focus is more on AAR that can be performed locally on the animal itself and use as little energy as possible.…”