Scalable Injury-Risk Screening in Baseball Pitching From Broadcast Video

TL;DR

This paper introduces a scalable method to extract biomechanical metrics from broadcast baseball videos for injury risk prediction, achieving high accuracy and enabling injury screening outside professional stadiums.

Contribution

A novel monocular video pipeline that recovers 18 biomechanics metrics from broadcast footage, facilitating injury prediction without expensive multi-camera systems.

Findings

Achieves sub-degree accuracy for 16 out of 18 metrics

AUC of 0.811 for Tommy John surgery prediction

AUC of 0.825 for significant arm injuries

Abstract

Injury prediction in pitching depends on precise biomechanical signals, yet gold-standard measurements come from expensive, stadium-installed multi-camera systems that are unavailable outside professional venues. We present a monocular video pipeline that recovers 18 clinically relevant biomechanics metrics from broadcast footage, positioning pose-derived kinematics as a scalable source for injury-risk modeling. Built on DreamPose3D, our approach introduces a drift-controlled global lifting module that recovers pelvis trajectory via velocity-based parameterization and sliding-window inference, lifting pelvis-rooted poses into global space. To address motion blur, compression artifacts, and extreme pitching poses, we incorporate a kinematics refinement pipeline with bone-length constraints, joint-limited inverse kinematics, smoothing, and symmetry constraints to ensure temporally stable and physically plausible kinematics. On 13 professional pitchers (156 paired pitches), 16/18 metrics achieve sub-degree agreement (MAE $< 1^{\circ}$). Using these metrics for injury prediction, an automated screening model achieves AUC 0.811 for Tommy John surgery and 0.825 for significant arm injuries on 7,348 pitchers. The resulting pose-derived metrics support scalable injury-risk screening, establishing monocular broadcast video as a viable alternative to stadium-scale motion capture for biomechanics.