Prediction of on-field rugby scrummaging contact forces from videos using artificial neural networks

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Mean correlation coefficient 0.95 ± 0.05

• Primary Outcome: Correlation between predicted and measured contact forces

• Nnt Or Sensitivity: Mean normalized RMSE 9.3 ± 4.3%, mean normalized absolute difference in peak force 6.7 ± 5.5%

• Confidence Interval: Not explicitly reported

Clinical Application

Technically feasible but requires specialized equipment and expertise for implementation in clinical or sporting contexts Relevant to Australian rugby union and league, particularly for Rugby Australia and NRL injury prevention initiatives, though would require local validation studies Rugby players, particularly forwards involved in scrummaging, though generalizability uncertain

Abstract

Rugby is a contact sport with a high risk of injury. Scrums are a key component of the game and represent a collision event associated with serious injuries, especially to the cervical spine. Traditional methods for measuring scrum forces rely on both pressure sensors and scrum machines, but these have limitations for on-field monitoring. Thus, this study investigates the feasibility of using a machine learning approach to predict contact forces in rugby scrummaging during real-game situations, based on only anatomical landmarks of players extracted from video footage. A recurrent neural network (RNN) model was trained to predict contact forces from velocity signals. A dataset of eleven rugby teams (22 forward packs, n = 176 players) during on-field scrum engagements was used. Data augmentation techniques using a generative adversarial network and the Mixup technique were applied to increase the size of the training dataset. The RNN was trained using time-dependent data, with 2D trajectories from video landmarks as inputs and force signals from pressure sensors as outputs. The RNN´s prediction results showed good to excellent agreement between the predicted and measured time-dependent normal contact force signals, with a mean correlation of 0.95 ± 0.05. The mean normalized RMSE was 9.3 ± 4.3% and the mean normalized absolute difference in peak force was 6.7 ± 5.5%. This study demonstrated the feasibility of using RNNs to quantify contact forces in rugby scrummaging using only single-camera video, without players wearing sensors. In combination with a 2D human pose estimation model, the ANN trained in this study could support performance analysis, coaching, technique correction, and injury prediction using in-game data.

References

1. 1.Cordero-Sánchez, J., Sheehy, Z., Serrancolí, G., Preatoni, E., Trewartha, G., & Cazzola, D. (2024). Prediction of on-field rugby scrummaging contact forces from videos using artificial neural networks. PLoS One, 19(9), e0330097. https://doi.org/10.1371/journal.pone.0330097