A Deep Dive Into Current Marker-Less Motion Capture Systems and Integrating Theia3D Outputs Into OpenSim
Bibliographic record
Abstract
This project aimed to explore the various marker-less motion capture systems available for biomechanical analysis and identify the most suitable option for our laboratory. Marker-less systems are becoming more prominent in biomechanical analysis due to their non-invasive approach and reduced data collection time. Upon choosing an appropriate marker-less system, the biggest challenge was integrating the output into OpenSim, a flexible platform that provides musculoskeletal modelling. The initial leg of this research compared the different marker-less systems available and how accurately they compared to marker-based systems. The variables considered included accuracy, precision, hardware, coordinate system, and more. The systems included Deep Lab Cut, Theia3D, Open Pose, HRnet, DARI motion. Upon comparison, it was decided objectively that Theia3D provided the most accurate calculations, but the output produced was difficult to integrate into other 3D models. The default 3D model produced by Theia3D used Visual3D, which cannot be altered through MATLAB. As a result, the next step of the research was to produce a script that could manipulate the Theia3D data so that it could be read and imported into OpenSim. The subsequent phase of this research required developing the outputs of Theia3D data into a file compatible with OpenSim. A sample script with a similar goal was provided and used as a framework for the task. The existing script provided an outline of how to process Theia3D data and extract segment angles but required a method to save the variables in an OpenSim compatible format. The final and ongoing step of the research requires this code to be integrated into MATLAB and produce a GUI that would allow specific angles to be extracted from a dataset.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.027 | 0.014 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".