Assessing the Accuracy of Markerless Motion Capture for High-Speed Baseball Pitching

December 2, 2025
Theia
BIO
Recent Posts
New Research on Theia3D: Comparing Markerless and Marker-Based Shoulder Kinematics Across Full Arm Range of Motion
A 2025 study published in the Journal of Biomechanics compared shoulder kinematics measured with Theia3D markerless motion capture against gold-standard marker-based motion capture across full arm ranges of motion. The results show strong agreement for many movements, particularly in the coronal plane, while also highlighting where caution is still required, especially at the extremes of ranges of motion and in transverse-plane rotations.
Baseball Tracking System: A Practical Guide to Evaluating Your Options
Baseball tracking systems can measure everything from ball flight and bat path to workload and full-body biomechanics, but each category answers a different question. This guide compares leading options and explains how to choose the right system based on what your program needs to measure, where it will operate, and whether it can connect athlete mechanics to baseball outcomes.
How to Choose Motion Analysis Software: Features, Accuracy, and Workflow Fit
Choosing motion analysis software depends on more than whether it can track movement. This guide compares leading tools by output type, setup complexity, validation, data ownership, and workflow fit so research and performance teams can choose the right system for their needs.

Summary

A new peer-reviewed study published in the Journal of Sports Sciences (Nov 2025) evaluated the accuracy of two multi-camera markerless motion capture systems – including Theia3D – against a marker-based reference during high-speed baseball pitching. Using synchronized captures from 18 collegiate pitchers throwing max-effort fastballs in an MLB stadium, the study assessed joint position accuracy, kinematic waveform agreement, and kinetic metrics, validating markerless motion capture for high-speed athletic movement analysis.

Editor's Note: The following summary details independent academic research conducted in clinical research settings. Theia3D is an offline software solution engineered exclusively for research and human performance analysis.

Note: These findings illustrate how differences in system architecture, camera configuration, and keypoint detection modelling may influence accuracy, particularly in high-speed, multi-planar movements such as baseball pitching. These results should not be interpreted as demonstrating inherent superiority of one ML system over another, but rather as evidence of how specific design characteristics manifest in measured biomechanical outcomes.


Why This Matters
‍

Pitching is one of the most complex and high-velocity movements in sport. This paper delivers strong independent evidence that multi-camera markerless systems can estimate pitching kinematics and key metrics with practical reliability, particularly when camera placement is optimized (as in a Theia3D deployment).

Study Overview

  • Participants: 18 NCAA D1/D2 pitchers
  • Setting: Petco Park (MLB stadium)
  • Task: Ten max-effort fastballs per athlete
  • Systems: Theia3D (10 Qualisys Miqus cameras), Hawk-Eye (5 in-stadium cameras), Marker-based reference (18 Qualisys Arqus cameras)

Key Findings
‍

Mean per-joint position error: Theia3D 52.0 ± 12.3 mm vs. Hawk-Eye 56.6 ± 9.4 mm. Consistent agreement was demonstrated for stride length (CCC > 0.85), pelvis rotation, trunk rotation, and shoulder rotational velocity. Upper-extremity velocities showed expected variability consistent with literature.

What This Means for Baseball Biomechanics
‍

For MLB/NCAA performance staff, Theia3D enables analysis of pelvis-trunk sequencing, stride mechanics, and timing chain events foundational to velocity and repeatability. The study provides the first published evaluation of kinetic outputs from any ML system during pitching.

Access the full study here.
‍

Interested in Markerless Biomechanics for Baseball?
‍

Contact us today to book a demo.

Recent Posts
New Research on Theia3D: Comparing Markerless and Marker-Based Shoulder Kinematics Across Full Arm Range of Motion
A 2025 study published in the Journal of Biomechanics compared shoulder kinematics measured with Theia3D markerless motion capture against gold-standard marker-based motion capture across full arm ranges of motion. The results show strong agreement for many movements, particularly in the coronal plane, while also highlighting where caution is still required, especially at the extremes of ranges of motion and in transverse-plane rotations.
Baseball Tracking System: A Practical Guide to Evaluating Your Options
Baseball tracking systems can measure everything from ball flight and bat path to workload and full-body biomechanics, but each category answers a different question. This guide compares leading options and explains how to choose the right system based on what your program needs to measure, where it will operate, and whether it can connect athlete mechanics to baseball outcomes.
How to Choose Motion Analysis Software: Features, Accuracy, and Workflow Fit
Choosing motion analysis software depends on more than whether it can track movement. This guide compares leading tools by output type, setup complexity, validation, data ownership, and workflow fit so research and performance teams can choose the right system for their needs.
In this blog
Summary