Validation of markerless vision-based motion capture for ergonomics risk assessment
Bibliographic record
Abstract
Work-related musculoskeletal disorders impact millions annually, often due to awkward postures and heavy lifting. Vision-based markerless optical motion capture (ML-OMC) systems have gained attention as a possible solution for identifying ergonomic risks in workplace settings. However, their reliability remains unknown compared to marker-based optical motion capture (MB-OMC) and inertial measurement units (IMUs). This study reports on a comparative analysis of an ML-OMC against MB-OMC and IMUs and its suitability for joint reaction force estimation. Eight participants performed lifting, a task considered physically demanding among manual handling activities, while their joint angles were recorded using the three measurement systems, and joint reaction forces were determined using joint angle data and ground reaction forces through biomechanical modeling. Furthermore, postural ergonomic assessment scores were computed for the lifting initiation posture of the activity using data from the three systems and biomechanics experts’ inputs. The back angle obtained by ML-OMC exhibited a strong correlation (0.95) with both MB-OMC and IMUs, along with small RMSE values of 6.5° and 9.9° compared to the readouts from MB-OMC and IMUs, respectively. The L5-S1 joint reaction forces obtained by ML-OMC showed a high correlation (0.91 with MB-OMC and 0.85 with IMUs), and small RMSE and normalized RMSE values. Additionally, postural ergonomic assessment scores obtained from ML-OMC aligned with MB-OMC for 87 % of participants, showing significant consistency compared to the notable variation seen with expert-derived scores. These findings underscore the potential of ML-OMC as a dependable in-field ergonomic risk assessment tool for preventing work-related musculoskeletal disorders.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".