MétaCan
Menu
Back to cohort

Two cameras can be as good as four for markerless hand tracking during simple finger movements

2025· article· en· W4406757985 on OpenAlexafffund
Daanish M. Mulla, Nigel Majoni, Paul M Tilley, Peter J. Keir

Bibliographic record

VenueJournal of Biomechanics · 2025
Typearticle
Languageen
FieldComputer Science
TopicHand Gesture Recognition Systems
Canadian institutionsMcMaster University
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsSimple (philosophy)Computer visionTracking (education)Artificial intelligenceComputer scienceMovement (music)PsychologyArtAestheticsPhilosophy

Abstract

fetched live from OpenAlex

Recording and quantifying hand and finger movement is essential for understanding the neuromechanical control of the hand. Typically, kinematics are collected through marker-based optoelectronic motion capture systems. However, marker-based systems are time-consuming to setup, expensive, and cumbersome, especially for finger tracking. Advances in markerless systems have potential to overcome these limitations, as demonstrated by recent applications in lower extremity biomechanics research. In this work, we aimed to integrate markerless systems for hand biomechanics research by combining open source markerless motion capture pipelines (MediaPipe and Anipose) and investigating the number of cameras required for tracking single finger flexion-extension movements. Finger movements were recorded at three different speeds (0.50, 0.75, 1 Hz) for each of the instructed fingers (index, middle, ring, little) using 4 webcams. Finger joint angles were compared when using all 4 webcams for triangulating 3D hand key points versus all 2- and 3-camera subset combinations. The number of cameras was found to affect joint angles, with differences up to 20° when using 2 or 3 cameras compared to using all 4 cameras. However, we found some 2-camera orientations had minimal differences compared to using all 4 cameras (< 4° difference for the sum of finger [metacarpal, proximal interphalangeal, and distal phalangeal] joint angles). Thus, there can be little to no benefit of adding more than 2 cameras for 3D markerless tracking of the hand during single finger flexion-extension with optimal camera placement.

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 imitation

Not 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.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.011
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.028
Threshold uncertainty score0.094

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.011
Meta-epidemiology (narrow)0.0020.002
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0020.001
Science and technology studies0.0010.001
Scholarly communication0.0020.004
Open science0.0020.002
Research integrity0.0030.001
Insufficient payload (model declined to judge)0.0280.007

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 head0.024
GPT teacher head0.296
Teacher spread0.272 · 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 source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
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

Citations11
Published2025
Admission routes2
Has abstractyes

Explore more

Same venueJournal of BiomechanicsSame topicHand Gesture Recognition SystemsFrench-language works237,207