Predicting Athlete Ground Reaction Forces and Moments From Spatio-Temporal Driven CNN Models

摘要

The accurate prediction of three-dimensional (3-D) ground reaction forces and moments (GRF/Ms) outside the laboratory setting would represent a watershed for on-field biomechanical analysis. To extricate the biomechanist's reliance on ground embedded force plates, this study sought to improve on an earlier partial least squares (PLS) approach by using deep learning to predict 3-D GRF/Ms from legacy marker based motion capture sidestepping trials, ranking multivariate regression of GRF/Ms from five convolutional neural network (CNN) models. In a possible first for biomechanics, tactical feature engineering techniques were used to compress space-time and facilitate fine-tuning from three pretrained CNNs, from which a model derivative of ImageNet called "CaffeNet" achieved the strongest average correlation to ground truth GRF/Ms r (F-mean) 0.9881 and r (M-mean) 0.9715 (rRMSE 4.31 and 7.04%). These results demonstrate the power of CNN models to facilitate real-world multivariate regression with practical application for spatio-temporal sports analytics.