Validity of neural networks in determining lower limb kinematics in stationary cycling

Abstract

PurposeIncreasing access to marker-less technology has enabled practitioners to obtain kinematic data more quickly. However, the validation of many of these methods is lacking. Therefore, the validity of pre-trained neural networks was explored in this study compared to reflective marker tracking from sagittal plane cycling motion.MethodsTwenty-six cyclists were assessed during stationary cycling at self-selected cadence and moderate intensity exercise. Standard video from their sagittal plane was obtained to extract joint kinematics. Hip, knee, and ankle angles were calculated from marker digitisation and from two deep learning-based approaches (TransPose and MediaPipe).ResultsTypical errors ranged between 1 and 10° for TransPose and 3–9° for MediaPipe. Correlations between joint angles calculated from TransPose and marker digitalization were stronger (0.47–0.98) than those from MediaPipe (0.25–0.96).ConclusionTransPose seemed to perform better than MediaPipe but both methods presented poor performance when tracking the foot and ankle. This seems to be associated with the low frame rate and image resolution when using standard video mode.