Deep-Learning-Based Recovery of Missing Optical Marker Trajectories in 3D Motion Capture Systems
Open Access
- 1 June 2024
- journal article
- research article
- Published by MDPI AG in Bioengineering
- Vol. 11 (6) , 560
Abstract
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.Keywords
Funding Information
- Ministry of Trade, Industry and Energy (20016285, 2021R1A2C1009951)
- National Research Foundation of Korea (20016285, 2021R1A2C1009951)
This publication has 49 references indexed in Scilit:
- Comparing Long Short-Term Memory (LSTM) and bidirectional LSTM deep neural networks for power consumption predictionEnergy Reports, 2023
- Robustified extreme learning machine regression with applications in outlier-blended wind-speed forecastingApplied Soft Computing, 2022
- DeMoCap: Low-Cost Marker-Based Motion CaptureInternational Journal of Computer Vision, 2021
- Predictions for COVID-19 with deep learning models of LSTM, GRU and Bi-LSTMChaos, Solitons & Fractals, 2020
- Acquisition of point cloud in CT image space to improve accuracy of surface registration: Application to neurosurgical navigation systemJournal of Mechanical Science and Technology, 2020
- Predicting running injury using kinematic and kinetic parameters generated by an optical motion capture systemSN Applied Sciences, 2019
- Designing a camera placement assistance system for human motion capture based on a guided genetic algorithmVirtual Reality, 2017
- A multi-camera calibration method using a 3-axis frame and wandInternational Journal of Precision Engineering and Manufacturing, 2012
- Real-time marker prediction and CoR estimation in optical motion captureThe Visual Computer, 2012
- Estimation of missing markers in human motion captureThe Visual Computer, 2006