Human movement rebuilt from video during assisted and quick actions
Human movement reconstruction through latent structural representations during assisted transitions and multidirectional hopping
Computational Engineering, Finance, and Science
Summary
Measuring how people move in three dimensions is important for helping those with physical challenges and studying muscles and joints. The authors tested a new video-based method that uses artificial intelligence to fill in missing details when people move quickly or with help from others. They showed this method works for children with and without physical impairments and for a young adult hopping in many directions. The method can predict body positions and joint angles with reasonable accuracy, connecting computer analysis with real movement patterns.
What this means in practice
- •For physical therapists: Assess complex patient movements more accurately using video without full sensor setups.
- •For sports trainers: Analyze high-speed athletic movements from video to improve training and injury prevention.
Authors
Guilherme Manna Cesar, Ligia Yumi Mochida, Chady Ghnatios
Abstract
The quantification of three-dimensional human kinematics is fundamental to neurorehabilitation and musculoskeletal research, yet atypical posture, physical assistance, and rapid movement create conditions of partial observability. Here, we evaluate a latent-structure-informed framework combining convolutional rank-reduction autoencoding with feedforward regression to reconstruct movement from synchronized video. Three case-based demonstrations span therapist-assisted sit-to-stand in a child with cerebral palsy, unassisted sit-to-stand in a typically developing child, and multidirectional single-leg hopping in a young adult. Reconstruction was examined through positional trajectories, projected angular descriptors, and hip-knee coupling. Across test repetitions excluded from model training, mean absolute errors in a predicted marker position during assisted sit-to-stand ranged from 12.02 to 57.11 mm. Sagittal knee and trunk descriptor errors were 5.32° and 5.38° in the typically developing case. Hip-knee cyclograms captured aspects of coupled-motion patterns in both cases, with closer trajectory correspondence in the typically developing case. Sixteen test hops yielded a vertical knee-marker mean absolute error of 15.58 mm. These findings connect latent-structure-informed reconstruction with biomechanically interpretable movement features, providing a foundation for video-derived assessment spanning clinically atypical movement and high-dynamic athletic movement.