Uncertainty-Aware Mapping from 3D Keypoints to Anatomical Landmarks for Markerless Biomechanics

2026-03-27

AI Summary

This study addresses a critical limitation in existing markerless biomechanical methods: the neglect of estimation uncertainty when mapping 3D keypoints to anatomical landmarks, resulting in a lack of per-frame quality control. The work proposes the first temporal learning framework that explicitly models uncertainties arising from both observational noise and model limitations, leveraging them as an intrinsic mechanism for automatic quality assessment to quantify mapping confidence. Through comprehensive analyses—including error–uncertainty correlation, risk–coverage evaluation, and anomaly detection—the authors demonstrate that model uncertainty is a dominant indicator of mapping failure. Experimental results show a strong correlation between predicted uncertainty and landmark error (Spearman ρ ≈ 0.63); at 10% coverage, the average error drops to 16.8 mm, and the method achieves a ROC-AUC of 0.92 in detecting severe errors exceeding 50 mm.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Uncertainty Representations
• Intelligent Robots: State Estimation

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Markerless biomechanics increasingly relies on 3D skeletal keypoints extracted from video, yet downstream biomechanical mappings typically treat these estimates as deterministic, providing no principled mechanism for frame-wise quality control. In this work, we investigate predictive uncertainty as a quantitative measure of confidence for mapping 3D pose keypoints to 3D anatomical landmarks, a critical step preceding inverse kinematics and musculoskeletal analysis. Within a temporal learning framework, we model both uncertainty arising from observation noise and uncertainty related to model limitations. Using synchronized motion capture ground truth on AMASS, we evaluate uncertainty at frame and joint level through error--uncertainty rank correlation, risk--coverage analysis, and catastrophic outlier detection. Across experiments, uncertainty estimates, particularly those associated with model uncertainty, exhibit a strong monotonic association with landmark error (Spearman $ρ\approx 0.63$), enabling selective retention of reliable frames (error reduced to $\approx 16.8$ mm at 10% coverage) and accurate detection of severe failures (ROC-AUC $\approx 0.92$ for errors $>50$ mm). Reliability ranking remains stable under controlled input degradation, including Gaussian noise and simulated missing joints. In contrast, uncertainty attributable to observation noise provides limited additional benefit in this setting, suggesting that dominant failures in keypoint-to-landmark mapping are driven primarily by model uncertainty. Our results establish predictive uncertainty as a practical, frame-wise tool for automatic quality control in markerless biomechanical pipelines.

Problem

• markerless biomechanics
• 3D anatomical landmarks
• predictive uncertainty
• keypoint-to-landmark mapping
• quality control

Innovation

• predictive uncertainty
• markerless biomechanics
• anatomical landmark mapping
• model uncertainty
• quality control