MétaCan
Menu
Back to cohort
Record W4405598309 · doi:10.2196/56682

Quantifying Similarities Between MediaPipe and a Known Standard to Address Issues in Tracking 2D Upper Limb Trajectories: Proof of Concept Study

2024· article· en· W4405598309 on OpenAlexafffundvenue
Vaidehi Wagh, Matthew W. Scott, Sarah N. Kraeutner

Bibliographic record

VenueJMIR Formative Research · 2024
Typearticle
Languageen
FieldMedicine
TopicStroke Rehabilitation and Recovery
Canadian institutionsUniversity of British ColumbiaUniversity of British Columbia, Okanagan Campus
FundersNatural Sciences and Engineering Research Council of CanadaMitacs
KeywordsArtificial intelligenceTouchscreenComputer visionComputer scienceMean squared errorResamplingNormalization (sociology)MathematicsStatistics

Abstract

fetched live from OpenAlex

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 imitation

Not 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.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Qualitative · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.289
Threshold uncertainty score0.451

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.121
GPT teacher head0.474
Teacher spread0.353 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designQualitative
Domainnot available
GenreEmpirical

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".

Quick stats

Citations21
Published2024
Admission routes3
Has abstractyes

Explore more

Same venueJMIR Formative ResearchSame topicStroke Rehabilitation and RecoveryFrench-language works237,207