OpenCap Monocular: 3D Human Kinematics and Musculoskeletal Dynamics from a Single Smartphone Video

Dimensions overall score 8.0

GitHub Code Pulse

No public code linked for this paper yet.

• OpenCap Monocular estimates 3D skeletal kinematics and kinetics from a single smartphone video with low kinematic error (4.8° mean absolute error for rotational degrees of freedom; 3.4 cm for pelvis translations).result 95%
• OpenCap Monocular outperforms a regression-only computer vision baseline by 48% in rotational accuracy and 69% in translational accuracy.result 93%
• OpenCap Monocular estimates ground reaction forces during walking with accuracy comparable to or better than the prior two-camera OpenCap system.result 90%
• The algorithm estimates clinically meaningful kinetic outcomes including knee extension moment during sit-to-stand transitions and knee adduction moment during walking.result 88%
• OpenCap Monocular refines 3D human pose estimates from WHAM via optimization, computes kinematics of a biomechanically constrained skeletal model, and estimates kinetics via physics-based simulation and machine learning.method 92%
• The algorithm's accuracy relies on good video quality and lighting, and it assumes static camera setups, limiting its use in dynamic or poorly lit environments.limitation 91%
• OpenCap Monocular is deployed via a smartphone app, web app, and secure cloud computing, enabling free, accessible single-smartphone biomechanical assessments.technical 94%
• The technology democratizes access to advanced biomechanical analysis tools by making them accessible through smartphones rather than requiring expensive specialized lab equipment.market 85%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card