OpenCap Monocular: 3D Human Kinematics and Dynamics From a Single Smartphone

OpenCap Monocular estimates 3D human kinematics and musculoskeletal dynamics from a single static smartphone video. It is validated against marker-based motion capture for walking, squatting, and sit-to-stand activities and is free and open-source.

Key outputs include joint kinematics and kinetics, and example tasks are documented alongside videos and figures on this page.

Quantifying human movement (kinematics) and musculoskeletal forces (kinetics) at scale--such as estimating quadriceps force during a sit-to-stand movement--could transform the prediction, treatment, and monitoring of mobility-related conditions. However, traditional motion analysis requires costly and time-intensive laboratory systems, which limit clinical translation. Scalable, accurate tools for biomechanical assessment are critically needed. We introduce OpenCap Monocular, an algorithm that estimates 3D kinematics and kinetics from a single static smartphone video. The method refines 3D human pose estimates from a monocular pose estimation model from computer vision (WHAM) via optimization, computes the kinematics of a biomechanically constrained skeletal model, and estimates kinetics via physics-based simulation and machine learning. We validated OpenCap Monocular against marker-based motion capture and force plate data for walking, squatting, and sit-to-stand tasks. OpenCap Monocular achieved low kinematic error (4.8° rotational mean absolute error [MAE]; 3.4 cm translational MAE), outperforming a regression-only computer vision baseline (9.3° rotational MAE; 11.0 cm translational MAE). It also estimated ground reaction forces during walking with accuracy comparable to, or better than, that of our prior two-camera OpenCap system. We demonstrate clinically meaningful accuracy in applications related to frailty and knee osteoarthritis, including estimating the knee extension moment during sit-to-stand transitions and the knee adduction moment during walking. OpenCap Monocular is deployed via a smartphone app and secure cloud computing, enabling free, accessible single-smartphone biomechanical assessments. Such accessibility enables large-scale remote studies and, ultimately, routine evaluations of mobility and function in the clinic or at home. Our code is available at github.com/utahmobl/opencap-monocular.