TECHNOLOGY

DATASET

Unique datasets of motion and force data during rugby tackling, sprinting, jumping, and change of direction

BIOMECHANICS

10 years of research in computational biomechanics and musculoskeletal models creation and validation

PHYSICS-INFORMED AI

We implement the laws of physics in the form of differential equations in our machine learning models

GENERATIVE AI

We leverage generative AI approaches to create realistic scenario-based simulations of sport performance

How It Works

POSE ESTIMATION

Screenshot 2024-12-07 at 20.40_edited.jpg

We use computer vision to extract player movement data from single (2D) or multiple (3D) cameras video footage. By retraining pose estimation algorithms we accurately track joint positions and then calculate joint angles using inverse kinematics approaches.

FORCE ESTIMATION

Using physics-based machine learning, we go beyond motion tracking and estimate the forces experienced or generated by players on the pitch. This includes ground reaction forces, collision forces, and joint-level forces, providing a comprehensive understanding of the physical demands placed on athletes during performance or gameplay.

ACTIONABLE INSIGHTS

AEnB2UoGScBfT783YjM3MuM-pboIXuHMPbfk2TSo

We leverage coaching theories, expertise, and professional experience to create advanced coaching algorithms that transform biomechanical data into practical, actionable insights. Coaches and athletes gain access to key performance metrics and tailored recommendations, empowering them to enhance performance, monitor training loads, and minimize injury risks — all in an intuitive, user-friendly format.

FROM MOTION TO FORCES

We leverage unique datasets of athletes motion and forces, to train Physics-Informed AI solutions that enable to measure collision or ground reaction forces from videos.

RUGBY TACKLING DATABASE

SPRINTING DATABASE

Use Cases

RUGBY TACKLING
Multiperson Tracking

10m SPRINT
Ground Reaction Force

RUGBY SCRUM
Force Estimation

Scientific Work

Please use the button below to access the list of references of the academic work published on peer-reviewed journals that contributed to the creation and validation of the Forceteck algorithms.

Silvestros, P., Quarrington, R. D., Preatoni, E., Gill, H. S., Jones, C. F., & Cazzola, D. (2024). An Extended Neck Position is Likely to Produce Cervical Spine Injuries Through Buckling in Accidental Head-First Impacts During Rugby Tackling. Ann Biomed Eng. doi:10.1007/s10439-024-03576-z
Cowburn, J., Serrancolí, G., Pavei, G., Minetti, A., Salo, A., Colyer, S., & Cazzola, D. (2024). A novel computational framework for the estimation of internal musculoskeletal loading and muscle adaptation in hypogravity. Frontiers in Physiology, 15. doi:10.3389/fphys.2024.1329765
Seminati, E., Cazzola, D., Trewartha, G., & Preatoni, E. (2023). Tackle direction and preferred side affect upper body loads and movements in rugby union tackling. Sports Biomech, 1-17. doi:10.1080/14763141.2023.2201248
Haralabidis, N., Colyer, S. L., Serrancolí, G., Salo, A. I. T., & Cazzola, D. (2022). Modifications to the net knee moments lead to the greatest improvements in accelerative sprinting performance: a predictive simulation study. Scientific Reports, 12(1), 15908. doi:10.1038/s41598-022-20023-y
Lucas, D., Stokes, K., McGuigan, P., Hill, J., Cazzola, D., & Horse Racing Video Analysis Consensus Steering, G. (2022). Consensus on a jockey's injury prevention framework for video analysis: a modified Delphi study. BMJ Open Sport Exerc Med, 8(4), e001441. doi:10.1136/bmjsem-2022-001441
Haralabidis, N., Serrancolí, G., Colyer, S., Bezodis, I., Salo, A., & Cazzola, D. (2021). Three-dimensional data-tracking simulations of sprinting using a direct collocation optimal control approach. PeerJ, 9. doi:10.7717/peerj.10975
Silvestros, P., Pizzolato, C., Lloyd, D. G., Preatoni, E., Gill, H. S., & Cazzola, D. (2021). EMG-Assisted Neuromusculoskeletal Models Can Estimate Physiological Muscle Activations and Joint Moments Across the Neck Before Impacts. Journal of Biomechanical Engineering. doi:10.1115/1.4052555
Haralabidis, N., Saxby, D. J., Pizzolato, C., Needham, L., Cazzola, D., & Minahan, C. (2020). Fusing Accelerometry with Videography to Monitor the Effect of Fatigue on Punching Performance in Elite Boxers. Sensors, 20(20). doi:10.3390/s20205749
West, S. W., Williams, S., Cazzola, D., Kemp, S., Cross, M. J., & Stokes, K. A. (2020). Training Load and Injury Risk in Elite Rugby Union: The Largest Investigation to Date. Int J Sports Med(EFirst).
Silvestros, P., Preatoni, E., Gill, H. S., Gheduzzi, S., Hernandez, B. A., Holsgrove, T. P., & Cazzola, D. (2019). Musculoskeletal modelling of the human cervical spine for the investigation of injury mechanisms during axial impacts. PLoS One, 14(5), e0216663. doi:10.1371/journal.pone.0216663
Cazzola, D., Holsgrove, T. P., Preatoni, E., Gill, H. S., & Trewartha, G. (2017). Cervical Spine Injuries: A Whole-Body Musculoskeletal Model for the Analysis of Spinal Loading. PLoS One, 12(1), e0169329. doi:10.1371/journal.pone.0169329
Seminati, E., Cazzola, D., Preatoni, E., & Trewartha, G. (2017). Specific tackling situations affect the biomechanical demands experienced by rugby union players. Sports Biomech, 16(1), 58-75. doi:10.1080/14763141.2016.1194453
Cazzola, D., Stone, B., Holsgrove, T. P., Trewartha, G., & Preatoni, E. (2016). Spinal muscle activity in simulated rugby union scrummaging is affected by different engagement conditions. Scand J Med Sci Sports, 26(4), 432-440. doi:10.1111/sms.12446