Interpretable Pre-Release Baseball Pitch Type Anticipation from Broadcast 3D Kinematics
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910041760595968 |
|---|---|
| author | Bright, Jerrin Lu, Michelle Zelek, John |
| author_facet | Bright, Jerrin Lu, Michelle Zelek, John |
| contents | How much can a pitcher's body reveal about the upcoming pitch? We study this question at scale by classifying eight pitch types from monocular 3D pose sequences, without access to ball-flight data. Our pipeline chains a diffusion-based 3D pose backbone with automatic pitching-event detection, groundtruth-validated biomechanical feature extraction, and gradient-boosted classification over 229 kinematic features. Evaluated on 119,561 professional pitches, the largest such benchmark to date, we achieve 80.4\% accuracy using body kinematics alone. A systematic importance analysis reveals that upper-body mechanics contribute 64.9\% of the predictive signal versus 35.1\% for the lower body, with wrist position (14.8\%) and trunk lateral tilt emerging as the most informative joint group and biomechanical feature, respectively. We further show that grip-defined variants (four-seam vs.\ two-seam fastball) are not separable from pose, establishing an empirical ceiling near 80\% and delineating where kinematic information ends and ball-flight information begins. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_04874 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Interpretable Pre-Release Baseball Pitch Type Anticipation from Broadcast 3D Kinematics Bright, Jerrin Lu, Michelle Zelek, John Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning How much can a pitcher's body reveal about the upcoming pitch? We study this question at scale by classifying eight pitch types from monocular 3D pose sequences, without access to ball-flight data. Our pipeline chains a diffusion-based 3D pose backbone with automatic pitching-event detection, groundtruth-validated biomechanical feature extraction, and gradient-boosted classification over 229 kinematic features. Evaluated on 119,561 professional pitches, the largest such benchmark to date, we achieve 80.4\% accuracy using body kinematics alone. A systematic importance analysis reveals that upper-body mechanics contribute 64.9\% of the predictive signal versus 35.1\% for the lower body, with wrist position (14.8\%) and trunk lateral tilt emerging as the most informative joint group and biomechanical feature, respectively. We further show that grip-defined variants (four-seam vs.\ two-seam fastball) are not separable from pose, establishing an empirical ceiling near 80\% and delineating where kinematic information ends and ball-flight information begins. |
| title | Interpretable Pre-Release Baseball Pitch Type Anticipation from Broadcast 3D Kinematics |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2603.04874 |