Quantifying Similarities Between MediaPipe and a Known Standard to Address Issues in Tracking 2D Upper Limb Trajectories: Proof of Concept Study
Bibliographic record
Abstract
Background: Markerless motion tracking methods have promise for use in a range of domains, including clinical settings where traditional marker-based systems for human pose estimation are not feasible. Artificial intelligence (AI)-based systems can offer a markerless, lightweight approach to motion capture. However, the accuracy of such systems, such as MediaPipe, for tracking fine upper limb movements involving the hand has not been explored. Objective: The aim of this study is to evaluate the 2D accuracy of MediaPipe against a known standard. Methods: Participants (N=10) performed a touchscreen-based shape-tracing task requiring them to trace the trajectory of a moving cursor using their index finger. Cursor trajectories created a reoccurring or random shape at 5 different speeds (500-2500 ms, in increments of 500 ms). Movement trajectories on each trial were simultaneously captured by the touchscreen and a separate video camera. Movement coordinates for each trial were extracted from the touchscreen and compared to those predicted by MediaPipe. Specifically, following resampling, normalization, and Procrustes transformations, root-mean-squared error (RMSE; primary outcome measure) was calculated between predicted coordinates and those generated by the touchscreen computer. Results: Although there was some size distortion in the frame-by-frame estimates predicted by MediaPipe, shapes were similar between the 2 methods and transformations improved the general overlap and similarity of the shapes. The resultant mean RMSE between predicted coordinates and those generated by the touchscreen was 0.28 (SD 0.06) normalized px. Equivalence testing revealed that accuracy differed between MediaPipe and the touchscreen, but that the true difference was between 0 and 0.30 normalized px (t114=-3.02; P=.002). Additional analyses revealed no differences in resultant RMSE between methods when comparing across lower frame rates (30 and 60 frames per second [FPS]), although there was greater RMSE for 120 FPS than for 60 FPS (t35.43=-2.51; P=.03). Conclusions: Overall, we quantified similarities between one AI-based approach to motion capture and a known standard for tracking fine upper limb movements, informing applications of such systems in domains such as clinical and research settings. Future work should address accuracy in 3 dimensions to further validate the use of AI-based systems, including MediaPipe, in such domains.
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 | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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".