What does this research mean for the field?

In single-camera markerless motion capture, 2D pose estimation accuracy is highly sensitive to camera orientation, with oblique rear views being most accurate, whereas 3D mesh models provide more consistent estimates across angles but introduce anatomical bias requiring calibration. Novelty: ClaimNovelty.INCREMENTAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

This research aims to evaluate the accuracy of 2D and 3D pose estimation in estimating knee joint angles based on camera orientation.

April 5, 2026Open Access

Influence of camera orientation on joint-angle estimation using single-camera 2D and 3D markerless motion capture

Key Points

This research aims to evaluate the accuracy of 2D and 3D pose estimation in estimating knee joint angles based on camera orientation.
Assessed knee joint angle estimation using 2D (OpenPose) and 3D (GVHMR) algorithms across eight camera angles.
Compared results with traditional 3D marker-based motion capture.
Analyzed variability and performance of joint-angle calculations based on camera angles.
2D pose estimation showed significant variability in joint-angle calculations across different camera projections.
Oblique views (45°, 315°) provided the most accurate knee joint-angle estimates for the OpenPose algorithm.
The 3D mesh model (GVHMR) improved consistency across camera placements, but introduced calibration biases.

Abstract

Deep learning-based single-camera video pose estimation algorithms have shown promise for enabling large-scale movement studies in real-world environments, free from the limitations associated with marker-based and multi-camera markerless motion capture systems. However, there is limited research regarding the accuracy and applicability of human pose estimation in out-of-laboratory conditions. In single-camera systems, changes in camera projections can reduce joint visibility, increase occlusion, and lead to issues in observing multi-axial movements, which can affect the accuracy of calculating joint-angle estimates. This research aims to assess the performance and sensitivity of 2D (OpenPose) and 3D (GVHMR) reconstructions in estimating knee joint angle across eight camera angles compared to traditional 3D marker-based motion capture. 2D pose estimation (OpenPose) shows high variability in joint-angle calculations between camera projections, as oblique views, particularly rear view (45°, 315°), yielded the most accurate knee joint-angle estimates. For this algorithm, careful camera placement should be a consideration when collecting data. The addition of a 3D mesh model (GVHMR) helps generalize estimates across orientation, leading to more consistent results across camera placements. However, joint centers in these mesh models are not anatomically defined, introducing bias in the results that requires calibration. Single-camera markerless motion capture shows strong potential for clinical and sport settings, where rapid movement assessment is often preferred. However, important gaps remain in understanding how certain factors, such as configuration and occlusion, can affect joint angle-estimation accuracy. By quantifying how joint-angle outputs vary with camera angle across systems, this study offers practical guidance for system setup and clarifies the limitations and capabilities of single-view markerless motion capture for kinematic assessment.

Bookmark

View Full Paper