# Comparison of Kinematics and Kinetics Between OpenCap and a Marker-Based Motion Capture System in Cycling

arXiv: https://arxiv.org/abs/2409.03766 · HTML: https://mlsanity.com/paper/2409.03766/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 72 references that are in the map.
- First posted on arXiv 20 Aug 2024.

## Builds on (most cited first, 8 of 8)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Markerless tracking of user-defined features with deep learning](https://mlsanity.com/paper/1804.03142/) (2018)
- [Whole-Body Human Pose Estimation in the Wild](https://mlsanity.com/paper/2007.11858/) (2020)
- [Distribution-Aware Coordinate Representation for Human Pose Estimation](https://mlsanity.com/paper/1910.06278/) (2019)
- [Learnable Triangulation of Human Pose](https://mlsanity.com/paper/1905.05754/) (2019)
- [Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledge](https://mlsanity.com/paper/2211.11983/) (2022)

## Built on by (most cited first, 1 of 1)

- [Seeing Through Occlusion: Deterministic Arm Kinematic Correction for Robot Teleoperation](https://mlsanity.com/paper/2606.19240/) (2026)

## Abstract (arXiv)

This study evaluates the agreement of marker-based and markerless (OpenCap) motion capture systems in assessing joint kinematics and kinetics during cycling. Markerless systems, such as OpenCap, offer the advantage of capturing natural movements without physical markers, making them more practical for real-world applications. However, the agreement of OpenCap with a marker-based system, particularly in cycling, remains underexplored. Ten participants cycled at varying speeds and resistances while motion data were recorded using both systems. Key metrics, including joint angles, moments, and joint reaction loads, were computed using OpenSim and compared using root mean squared error (RMSE) per trial across participants, Pearson correlation coefficients (r) per trial across participants and repeated measures Bland-Altman to control trials dependency within subject. Results revealed very strong agreement (r GT 0.9) for hip (flexion/extension), knee (flexion/extension), and ankle (dorsiflexion/plantarflexion) joint angles.