Validation of pitchAI^TM markerless motion capture using marker-based 3D motion capture

ABSTRACT

This study sought to compare and validate baseball pitching mechanics, including joint angles and spatiotemporal parameters, from a single camera markerless motion capture solution with a 3D optical marker-based system. Ten healthy pitchers threw 2–3 maximum effort fastballs while concurrently using marker-based optical capture and pitchAI^TM (markerless) motion capture. Time-series measures were compared using R-squared (r²), and root mean square error (RMSE). Discrete kinematic measures at foot plant, maximal shoulder external rotation, and ball release, plus four spatiotemporal parameters were evaluated using descriptive statistics, Bland-Altman analyses, Pearson’s correlation coefficients, p-values, r², and RMSE. For time-series angles, r² ranged from 0.69 (glove arm shoulder external rotation) to 0.98 (trunk and pelvis rotation), and RMSE ranged from 4.37° (trunk lateral tilt) to 20.78° (glove arm shoulder external rotation). Bias for individual joint angle and spatiotemporal parameters ranged from −11.31 (glove arm shoulder horizontal abduction; MER) to 12.01 (ball visible). RMSE was 3.62 m/s for arm speed, 5.75% height for stride length and 21.75 ms for the ball visible metric. pitchAI^TM can be recommended as a markerless alternative to marker-based motion capture for quantifying pitching kinematics. A database of pitchAI^TM ranges should be established for comparison between systems.

KEYWORDS:

• Kinematics
• baseball
• pitching
• motion capture

Acknowledgements

Thank you to the athletes who participated in this study.

Disclosure statement

RB, MH, MS, CM are shareholders of the parent company ProPlayAI, which is a subsidiary of 3motionAI. CM is currently employed by 3motionAI.

Additional information

Funding

MH is supported by the Canada Research Chairs program (231151 NSERC CRC).