Extraction of gait characteristics in dogs using a mobile gait analysis system based on inertial sensors
Highlights
Abstract
This study aims to investigate two simple algorithms for extracting gait features from an inertial measurement unit (IMU)-based gait analysis system for dogs. The first algorithm was developed to determine the range of motion of hip/shoulder extension and flexion. The second algorithm automatically determines the stance and swing phase per leg. To investigate the accuracy of the algorithms, two dogs were measured simultaneously on a treadmill using an IMU system, an optical tracking system and two cameras. The estimation of the range of motion was compared with the optical tracking systems; a total of 280 steps were recorded. To check the recognition of stance and swing phases, a total of 63 steps were manually annotated in the video recordings and compared with the algorithm output.
The IMU-based estimation of the range of motion showed an average deviation of 1.4° to 5.6° compared to the visual reference, while the average deviation in recognising the start and end of the stance and swing phases was between -0.01 and 0.09 seconds. This study shows that even simple algorithms can extract relevant information from inertial measurements that is comparable to the results of more complex approaches. However, further studies with a larger number of subjects are required to investigate the significance of the results presented.
Read the scientific article in the Journal Veterinary and Animal Science, Volume 21, September 2023, 100301, for further insights.