Markerless Pixel-Based Pipeline for Quantifying 2D Lower Limb Kinematics During Squatting: A Preliminary Validation Study
Bibliographic record
Abstract
Background/Objectives: Marker-based motion capture remains widely used for lower limb kinematics due to its high precision, although its application is often constrained by elevated operational costs and the requirement for controlled laboratory environments. Markerless methods, such as MediaPipe offer a promising alternative for extending biomechanical analyses beyond traditional laboratory settings, but evidence supporting their validity in controlled tasks is still limited. This study aimed to validate a pixel-based markerless pipeline for two-dimensional kinematic analysis of hip and knee motion during squatting. Methods: Ten healthy volunteers performed three squats with a maximum depth of 90°. Kinematic data were collected simultaneously using marker-based and markerless systems. For the marker-based method, hip and knee joint angles were calculated from marker trajectories within a fixed coordinate system. For the markerless approach, a custom pixel-based pipeline was developed in MediaPipe 0.10.26 to compute bidimensional joint angles from screen coordinates. A paired t-test was conducted using Statistical Parametric Mapping, and maximum flexion values were compared between systems with Bland–Altman analysis. Total range of motion was also analyzed. Results: The markerless pipeline provided valid estimates of hip and knee motion, despite a systematic tendency to overestimate joint angles compared to the marker-based system, with a mean bias of −17.49° for the right hip (95% LoA: −51.89° to 16.91°). Conclusions: These findings support the use of markerless tools in clinical contexts where cost and accessibility are priorities, provided that systematic biases are taken into account during interpretation. Overall, despite the systematic differences, the 2D MediaPipe-based markerless system demonstrated sufficient consistency to assist clinical decision-making in settings where traditional motion capture is not available.
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 | 0.003 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".