Deep-Learning-Based Recovery of Missing Optical Marker Trajectories in 3D Motion Capture Systems

Motion capture (MoCap) technology, essential for biomechanics and motion analysis, faces challenges from data loss due to occlusions and technical issues. Traditional recovery methods, based on inter-marker relationships or independent marker treatment, have limitations. This study introduces a nove...

Full description

Saved in:
Bibliographic Details
Published in:Bioengineering (Basel) 2024-06, Vol.11 (6), p.560
Main Authors: Yuhai, Oleksandr, Choi, Ahnryul, Cho, Yubin, Kim, Hyunggun, Mun, Joung Hwan
Format: Article
Language:English
Subjects:
Accuracy
adaptive Huber loss
Algorithms
Analysis
artificial intelligence
Biomechanics
Cameras
Computer animation
Computer programs
data augmentation
Data integrity
Data loss
Datasets
Deep learning
Geospatial data
Interpolation
Long short-term memory
long-term missing data
Methods
Missing data
Motion capture
motion capture and analysis
multi-camera data integration
Outliers (statistics)
Reconstruction
Recovery
Statistical analysis
Statistical methods
Three dimensional motion
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Motion capture (MoCap) technology, essential for biomechanics and motion analysis, faces challenges from data loss due to occlusions and technical issues. Traditional recovery methods, based on inter-marker relationships or independent marker treatment, have limitations. This study introduces a novel U-net-inspired bi-directional long short-term memory (U-Bi-LSTM) autoencoder-based technique for recovering missing MoCap data across multi-camera setups. Leveraging multi-camera and triangulated 3D data, this method employs a sophisticated U-shaped deep learning structure with an adaptive Huber regression layer, enhancing outlier robustness and minimizing reconstruction errors, proving particularly beneficial for long-term data loss scenarios. Our approach surpasses traditional piecewise cubic spline and state-of-the-art sparse low rank methods, demonstrating statistically significant improvements in reconstruction error across various gap lengths and numbers. This research not only advances the technical capabilities of MoCap systems but also enriches the analytical tools available for biomechanical research, offering new possibilities for enhancing athletic performance, optimizing rehabilitation protocols, and developing personalized treatment plans based on precise biomechanical data.
ISSN:2306-5354
2306-5354
DOI:10.3390/bioengineering11060560