AI Pose Analysis and Kinematic Profiling of Range-of-Motion Variations in Resistance Training

TL;DR

This work addresses the lack of precise cross-exercise ROM characterization in resistance training by applying an AI pose-estimation pipeline to extract frame-level joint-angle time series from video data. A crossed random-effects meta-regression captures how $pROM$ and $fROM$ differ in ROM, tempo, and phase durations while partitioning variance into participant- and exercise-level components. Key findings show $pROM$ reduces ROM by about $59^{ ext{o}}$ and repetition duration by roughly $0.30$ s, with greater variability driven by participant differences; a data-driven $%ROM$ metric suggests lengthened partials average around $56 ext{ extperthousand}$ of $fROM$ (with one exception). These results demonstrate the feasibility of AI-driven kinematic profiling to inform standardized and individualized resistance-training prescriptions, while highlighting the need to monitor and account for increased variability in practice.

Abstract

This study develops an AI-based pose estimation pipeline to enable precise quantification of movement kinematics in resistance training. Using video data from Wolf et al. (2025), which compared lengthened partial (pROM) and full range-of-motion (fROM) training across eight upper-body exercises in 26 participants, 280 recordings were processed to extract frame-level joint-angle trajectories. After filtering and smoothing, per-set metrics were derived, including range of motion (ROM), tempo, and concentric/eccentric phase durations. A random-effects meta-analytic model was applied to account for within-participant and between-exercise variability. Results show that pROM repetitions were performed with a smaller ROM and shorter overall durations, particularly during the eccentric phase of movement. Variance analyses revealed that participant-level differences, rather than exercise-specific factors, were the primary driver of variation, although there is substantial evidence of heterogeneous treatment effects. We then introduce a novel metric, \%ROM, which is the proportion of full ROM achieved during pROM, and demonstrate that this definition of lengthened partials remains relatively consistent across exercises. Overall, these findings suggest that lengthened partials differ from full ROM training not only in ROM, but also in execution dynamics and consistency, highlighting the potential of AI-based methods for advancing research and improving resistance training prescription.